Translate findings, risks, and metrics into narratives leadership reads. Reference implementation of the Reporting category from RFC #38.

version
0.1.0
GitHub stars
436

Install

/plugin install grc-reporter@grc-engineering-suite

Run it inside Claude Code after adding the marketplace with /plugin marketplace add GRCEngClub/claude-grc-engineering.

Contents

Discovered from source

Skills 5

Automation Coverage Analysis

Week-over-week automation is the most under-sold thing GRC engineers do. A control moved from manual to automated is an hour given back to the team, a better evidence trail, and a compounding asset the next audit leverages without anyone thinking about it.

The analysis has to land the story, not the raw number.

Do not infer automation coverage from Finding remediation metadata alone. If the program did not record explicit automation metrics or curated notes, say the delta is unknown rather than inventing one.

The three anchors

Every automation-coverage report is built on three pieces. Pick the one that matters most for this period's audience and lead with it.

1. Time saved from humans

This is the headline most weeks.

Every automated control is hours back to a GRC analyst, security engineer, or auditor. Do not present automation as a technical metric. Present it as labor cost.

"We automated evidence collection for 12 controls this week" is the setup. "That's roughly 40 hours per audit cycle returned to the team, 160 hours per year" is the point.

Honest ranges beat fake precision. If the manual version took "between 2 and 4 hours per cycle," say that. Do not round up to make the number bigger.

2. Quality of evidence

This anchor matters most when the audience is an auditor, a regulator, or a security-posture-minded exec.

An automated control tested every hour is not the same as a manual control tested quarterly. Say that out loud.

"Before: we sampled 25 repositories annually. Now: every repository, every hour, every push."

That's a security posture change, not a tooling change. Frame it as one. This is where you earn engineering credit from security leadership, not just GRC leadership.

3. Forward-looking compounding value

This anchor is where you graduate from "did the work" to "shape the program."

Automation done is table stakes. The story is what it enables.

  • "This automation means the next SOC 2 audit is half the effort of the last one."
  • "This means we can onboard a new framework in 2 weeks instead of 12."
  • "This gives us continuous FedRAMP evidence, which means we stop batching evidence collection the week before the annual assessment."

The value of automation compounds. The narrative should show the compound. If you only report what got done, you're reporting tasks. If you report what it unlocks, you're reporting strategy.

Structure of a good automation-coverage report

Lead with one of the three anchors. Do not lead with the table. The table is proof, not message.

  1. Headline: time saved, quality lifted, or future impact. One line.
  2. The table: per-framework coverage, previous period, delta. Proof for the headline.
  3. What moved: name the controls automated only when the source data or operator notes explicitly identify them. Take-credit-by-name matters for retention, but invented names are worse than anonymous wins.
  4. What it unlocks: 1-3 bullets on downstream effects. This is where you pull on the compounding thread.
  5. Next targets: top 3-5 manually evidenced controls by cost. Not a full backlog. Just the priorities.

Anti-patterns

  • Reporting raw numbers without context. "5 controls automated" tells the reader nothing. "5 controls automated, saving 20 hours per cycle, closing a cross-framework gap in 3 baselines" tells them what happened.
  • Taking credit without naming people. Promotions happen when leadership sees specific engineers shipping specific wins. Anonymous program updates hide your team from their own leadership. Name the engineer.
  • Stopping at 'done.' A report that ends at "done this week" leaves the strategic thread on the floor. Always close with "what this enables next."
  • Performative ROI math. If the time savings are modest, say so. A modest win is still a win. Fake dollar figures cost credibility for the next six months.
  • Regressions swept under the rug. If a control moved automated → manual this week, name it, name the cause, name the fix plan. Silent regressions read as either sloppy reporting or hidden problems. Both are worse than the regression itself.

When to skip this report

Do not run this analysis in weeks where the pipeline only has one metric snapshot. The delta isn't real. Use context-bootstrap to explain why and schedule the next snapshot period instead.

Do not fabricate a week-over-week comparison to fill the slot. A missing report is better than a hollow one.

Picking the anchor for this week's audience

  • CISO or CIO weekly: time-saved anchor
  • Board or audit committee: forward-looking-value anchor
  • Audit planning meeting or pre-audit kickoff: quality-of-evidence anchor
  • Engineering leadership: any of the three, but name the engineer and show the compounding

If the audience isn't clear, default to time-saved. It's the most universally legible.

Context Bootstrap

Hollow reports are worse than no reports. When a user runs /report:exec-summary with an empty findings cache, the right move is to teach them the setup, not to make up a report.

What to check

Before any report command generates, verify:

  1. Plugins installed. Run /plugin list or inspect the marketplace. Need at least:

    • grc-engineer (the pipeline hub)
    • One connector (e.g., github-inspector, aws-inspector, okta-inspector)
    • One framework plugin (e.g., soc2, fedramp-rev5, iso27001)
  2. Findings cache populated. Look in ~/.cache/claude-grc/findings/<source>/*.json. Timestamps within the last 30 days mean the pipeline is active.

  3. Framework metadata available. Each framework plugin's plugin.json should have a framework_metadata block. Without it, coverage math fails silently.

  4. History depth (for week-over-week commands). /report:automation-coverage needs at least 2 metric snapshots in ./grc-data/metrics/ that are 7+ days apart. Verify snapshot dates there rather than inferring movement from the findings cache.

  5. Optional GitOps state. ./grc-data/risks/*, ./grc-data/metrics/*, ./grc-data/incidents/*.md. The JSON contracts live in docs/GRC-DATA.md. Missing is fine; present is better.

Command-specific minimums

  • /report:exec-summary: one connector, one framework, recent findings. Risks and metrics improve it but are not mandatory.
  • /report:program-health: two framework plugins plus one successful gap-assessment run per framework. A single-framework setup is not enough.
  • /report:board-brief: quarter-spanning findings history plus a real risk register if you want residual-risk sections to be grounded.
  • /report:automation-coverage: two metric snapshots in ./grc-data/metrics/ at least 7 days apart. Findings cache alone is not enough to claim week-over-week automation movement.

The three paths

Complete context

Auto-discover everything. Ask at most one or two narrative questions (audience, material asks). Generate.

Partial context

Name what's missing. Auto-discover what exists. Offer to proceed with interview mode where the user fills the gaps conversationally. Example:

I see findings from github-inspector across the last 14 days, SOC 2 framework installed. No risk register at ./grc-data/risks/. I can still write the report using findings and metrics only, or you can set up a risk register first. docs/GRC-DATA.md shows the file shape. Which do you want?

Empty context

Walk through the setup. Do not generate.

The empty-context setup script

Deliver these steps in plain conversational form. Do not dump all commands at once; confirm each step before moving to the next.

  1. Add the marketplace

    /plugin marketplace add GRCEngClub/claude-grc-engineering
    
  2. Install the minimum plugin set

    /plugin install grc-engineer@grc-engineering-suite
    /plugin install github-inspector@grc-engineering-suite
    /plugin install soc2@grc-engineering-suite
    

    github-inspector is the lowest-setup connector (uses the gh CLI you probably already have authenticated). soc2 is the most common first framework.

  3. Set up the connector

    /github-inspector:setup
    

    Confirms gh auth status and writes a default config.

  4. Collect findings

    /github-inspector:collect --scope=@me
    

    For a first run, @me scopes to the user's own repos. For org-wide scans, use --scope=<org-name> with a token that has admin:org.

  5. Run the first gap assessment (optional but recommended)

    /grc-engineer:gap-assessment SOC2 --sources=github-inspector
    

    Not strictly required for /report:* commands, but produces the crosswalked finding structure report commands read.

  6. Come back to the report command. With findings in cache, rerun the report command that sent the user here.

  7. If the user wants /report:program-health, add a second framework now.

    /plugin install fedramp-rev5@grc-engineering-suite
    /grc-engineer:gap-assessment SOC2,FedRAMP-Moderate --sources=github-inspector
    

    program-health needs more than one framework in scope or it is not a portfolio view.

For /report:automation-coverage specifically

This command needs history. If the user just finished a first-time setup, tell them:

You have one baseline from today. Automation coverage needs at least two metric snapshots 7+ days apart so there's a delta to report. Two options:

  1. Schedule regular collection with /grc-engineer:monitor-continuous SOC2 daily --sources=github-inspector. Come back in 7-14 days.
  2. Run /grc-engineer:record-automation-metrics <framework> --controls-total=<n> --controls-automated=<n> --window-label=<period> once per week so ./grc-data/metrics/ builds a real history, then rerun the report after you have two snapshots.

Do not fabricate a week-over-week comparison from Findings alone.

When to break the "no hollow report" rule

Never. A fake report is worse than no report because it teaches the user to trust numbers that aren't real. If the user explicitly asks for a template rendering with placeholder data for demo purposes, that is a different ask and gets a clearly-labeled DEMO DATA output.

Exec Narrative Patterns

Different readers want different things. The same findings should not land the same way in a board deck, a CISO 1:1, and a regulator response.

Audience quick reference

AudienceLength budgetOpening line wantsTechnical depthWhat they skip
Full board1 page maxStrategic posture one-linerLow. No control IDs in body.Operational detail, acronyms, tables with >5 rows
Audit committee2 pagesRisk-and-assurance postureMedium. Control families OK, not IDs.Strategy monologue, vendor names unless load-bearing
Risk committee2 pagesResidual risk movementMedium-high. Framework names, risk scoring.Program branding, tool selection detail
CEO weeklyHalf pageWhat changed, what's blocking, what's askedLow. Translate everything.Framework politics, tool comparisons
CISO weekly1 pageWhat moved, what's blocked, what's nextHigh. Control IDs, tool names, owner names fine.Over-explained context
Regulator / auditorAs long as neededPrecise scope + evidenceMaximum. IDs, artifact paths, timestamps.Narrative softening

Tone rules

Board and audit committee

  • Past tense for what happened. Present tense for posture. Future tense only for asks.
  • Numbers must be honest. Round where range matters more than precision. "Roughly 80%" beats "82.3%" if the instrument is noisy.
  • Never start with control IDs. Start with impact.
  • Name one person accountable per open item. Anonymous ownership reads as no ownership.

CEO weekly

  • Assume 90 seconds of attention.
  • Lead with the delta from last week. If nothing changed, say that.
  • Asks come with the decision you want, not the full context. Attach the context.

CISO weekly

  • Peer tone. You share context with the reader.
  • Bullets, not paragraphs.
  • Owner names and dates are load-bearing.

Regulator / auditor

  • Precision. Timestamps, scope statements, evidence paths.
  • Tone is neutral, not defensive. The facts do the work.

Format conventions

  • Headline row: one sentence, no hedging. If the week was quiet, the headline says so.
  • Tables beat prose for multi-framework status. Prose beats tables for narrative arcs.
  • Appendix is where detail lives. Body stays clean.
  • Dates are YYYY-MM-DD. Periods are YYYY-Q# or YYYY-W##.

Length tests

If you cannot defend every sentence as "the audience needed this to make a decision," cut it.

If the document opens with context before the point, invert it.

If there are three open items and no ask, you are reporting, not communicating. Add the ask.

Program Portfolio Composition

Most GRC programs run 3 to 8 frameworks. Presenting each one in full is how leadership reports get ignored. The job is to show the portfolio, not every control.

The SCF crosswalk is the unifier

Most "different" controls across frameworks map back to the same SCF control. SCF IAC-01 shows up as SOC 2 CC6.1, NIST AC-2, ISO A.9.2, CMMC AC.L2-3.1.1, and more. When you report the portfolio, collapse down to SCF first, then expand back to frameworks for the appendix.

A 15-framework program is usually a 400 SCF control program. That's the denominator that matters.

The 3 views that work

1. Coverage table (one row per framework)

FrameworkCoverage30-day deltaTop gapOwner
SOC 282%+3 ppAccess reviewsIAM

Five columns. Never more. If you need more, split into a second table with a clear break (e.g., "priority frameworks" vs "monitored frameworks").

2. Leverage list (cross-framework patterns)

Controls that fail in 3+ frameworks. Fix one, close many. This is the board-friendly version of "we are investing in the right things."

Example: "SCF IAC-15 (account-recertification) fails in SOC 2, FedRAMP, and ISO 27001. One automation project closes all three. Scoped for Q2."

3. Watch list (at-risk items)

Controls or frameworks trending down. Specifically name what could slip, why, and what prevents it.

What to drop from the portfolio view

  • Individual control status for anything that's green. It noise-floors the real signal.
  • Framework-specific language that doesn't translate. A SOC 2 person and a FedRAMP person use different vocabulary for the same thing. Use the SCF vocabulary in the body.
  • Every connector. Name the 2-3 that produce the most findings; relegate the rest to appendix.

What the appendix carries

  • Per-framework full gap reports, linked
  • SCF-to-framework crosswalk run ID
  • Connector inventory and coverage map
  • Any framework that was descoped this period, with reason

Red flags while composing

If the portfolio view is more than 2 pages, it has become the detailed report.

If the leverage list is empty, either you haven't mapped through SCF yet, or the program has no compounding work in flight. The first is a tooling fix. The second is a program problem worth naming.

If every framework shows identical coverage week over week, the pipeline isn't producing fresh findings. Flag this in the report rather than reporting stale numbers as if they were current.

So-What Translation

Every GRC person needs this skill and most don't have it. The controls are not the point. The frameworks are not the point. The deliverable is not the point. The point is the decision you want the reader to make.

These are the rules for translating the work into something a CISO or above will read, trust, and act on.

The 6 rules for talking with a CISO

1. They care about money

Not selfishly. Because their bosses care about money. The CFO, the CEO, the board. Every finding needs a dollar or time translation.

"We have a control deficiency in CC6.1" is invisible to a CISO. "This blocks a $2M SOC 2 deal closing in Q2" is not.

If you cannot translate a finding into dollars saved, dollars at risk, deals unblocked, or time returned to the team, you have not finished the work. Do that step before you walk into the room.

2. They don't care about GRC. They care about outcomes

More secure. More deals. Fewer surprises. Faster audits. Cleaner board meetings.

GRC is the plumbing. Nobody talks about plumbing at dinner. Talk about what's running through it: revenue, trust, speed, sleep. The controls and frameworks are how you get there. They are never the thing.

If your weekly update reads like a control checklist, you've written it wrong.

3. Excuses don't matter

What went wrong, and what are we doing about it.

"The connector failed this week" is not an update. "The connector failed Tuesday, we caught it by Thursday, here's the fix going in tomorrow, and here's what we're building so it can't happen again" is an update.

Every problem you name needs a response attached. If the response isn't ready, say "response in 48 hours, here's who owns it." Never leave a problem floating without an owner and a timeline.

4. Find out what they specifically care about

Every CISO has a personal scorecard. Budget defense. Security metrics the board sees. Making the CEO confident. Clean audits. Low-noise SOC. Getting promoted. Not getting fired.

You cannot communicate up effectively without knowing which of those scorecards you are moving this week. The only way to find out is to ask. In a 1:1. Directly.

"What do you want me making you look good on this quarter?" is a legitimate question from a GRC engineer to a CISO. Ask it.

5. Understand reporting lines

A CISO reporting to a CIO tells a different story than one reporting to a CEO.

  • CISO → CIO: budget defense, uptime, engineering velocity
  • CISO → CFO: cost of controls, audit spend, insurance posture
  • CISO → CEO: customer trust, regulatory exposure, board narrative
  • CISO → General Counsel: legal risk, regulatory posture, incident liability

Same finding, different framing, depending on whose ear you're actually reaching through the CISO.

6. Take initiative

Don't wait to be asked.

Bring the weekly update before it's requested. Bring the risk the board hasn't noticed yet. Bring the proposal for the automation project that didn't have a sponsor. Bring the framework expansion the company will need in 18 months.

The GRC engineers who rise are not the ones who execute the plan. They're the ones who name the next plan.

Patterns that land

  • "X open high-sev findings. Y block the audit. Plan attached."
  • "Automation shipped this week gives us 40 hours back per audit cycle."
  • "This finding maps across SOC 2 and FedRAMP. One fix, two closures. Owner: name. ETA: date."
  • "Residual risk moved from Medium to Low this quarter. Driver: specific control automation."

Patterns that don't

  • "We are 82% compliant." (Compliant with what? Measured how? Compared to when?)
  • "Ongoing monitoring continues." (This tells the reader nothing.)
  • Long paragraphs explaining framework history.
  • Control IDs in the body with no business translation.
  • Passive voice. "It was decided that..." Somebody decided. Name them.
  • Hedging. "We may want to consider..." If you're recommending it, recommend it.

Before publishing any exec-facing doc

Run this check on every section:

  1. Can a reader get the point in the first sentence?
  2. Is every open item owned by a named person with a date?
  3. Is every number defendable if questioned?
  4. Would the reader know what decision you want them to make?

If any answer is no, rewrite that section.

Commands 4

Automation Coverage

Report how much of your control portfolio is covered by automated evidence this week, how that compares to last week, and what the trend says about the GRC engineering work.

This is where GRC engineers prove their worth. Manual evidence is expensive and doesn't scale. Shifting a control from manual to automated is the engineering work that compounds. This command surfaces that work so leadership sees it.

Arguments

  • $1 - Period (optional, defaults to current week, e.g. 2026-W16)
  • $2 - Frameworks (optional, comma-separated framework aliases accepted by /grc-engineer:gap-assessment; defaults to all with current runs)

Instructions

1. Context check

Invoke context-bootstrap. Week-over-week analysis requires history:

  • At least 2 automation metric snapshots, at least 7 days apart, in ./grc-data/metrics/
  • Metric rows that make the delta explicit, typically automation.coverage_pct and automation.controls_automated
  • Framework metadata available in plugin.json files (for total control counts)
  • Findings runs in scope as supporting evidence, not as the primary source of automation coverage truth

If history is thin (0 or 1 runs, or runs clustered in the last few days), this command's empty-context path is the one users will hit. Do not fabricate a delta. Walk the user through:

  • Getting their first baseline into ./grc-data/metrics/ if they have none, usually with /grc-engineer:record-automation-metrics
  • Scheduling regular collection if they have one (/grc-engineer:monitor-continuous)
  • Setting a reminder to rerun this command once they have 2+ weeks of history

2. Auto-discover

  • Current-period metric rows for automation.coverage_pct and automation.controls_automated
  • Previous-period metric rows (closest to 7 days prior)
  • Total controls in scope per framework (from framework metadata)
  • Supporting findings runs per source for examples and appendix references
  • Regressions only when the source data or the operator's notes explicitly record them

Prefer operator-observed metric rows. Capability baselines derived from toolkit config are useful for setup and planning, but should not be presented as proof that a given environment already automated those controls.

3. Ask for narrative context

  • GRC engineering initiatives landing this period (helps attribute the delta to real work)
  • Any scope changes (new framework added, controls de-scoped) that affect the denominator
  • Audience - is this for CISO 1:1 (internal framing) or for a broader leadership update (more context needed)

4. Generate

Apply automation-coverage-analysis for the delta analysis and ROI framing. Apply so-what-translation for business-impact translation.

Do not infer manual → automated state from evaluations[].remediation.automation in Findings. That field describes remediation effort, not evidence-collection coverage.

Structure:

# Automation Coverage - <period>

## Headline
<One sentence. Coverage moved from X% to Y%. Z new controls automated this week.>

## Coverage Snapshot
| Framework | Total controls | Automated this period | Previous period | Delta |
|---|---|---|---|---|
| <fw> | <n> | <n (%)> | <n (%)> | <+/- n (+/- pp)> |

## What Moved This Period
### Gains
- <Metric-supported gain, and named controls only when the source data or operator notes explicitly identify them>

### Regressions (if any)
- <Only include when the source data explicitly records the regression and the cause>

## ROI Framing
<If prior-period manual evidence took X hours per cycle and the automated version is effectively free, this is the compounded saving. Avoid fake precision. Use honest ranges.>

## Next Targets
<Top 5 manually-evidenced controls by cost (frequency x hours) when the program tracks them. Otherwise, list next automation themes rather than pretending you have control-level precision.>

## Appendix
Current-period run: <run_id>
Previous-period run: <run_id>
Period delta: <days>

5. Save and offer next

Write to ./grc-reports/automation-coverage-<period>.md. Offer:

  • Commit the source metric rows to grc-data/metrics/ for longitudinal tracking
  • Use /grc-engineer:record-automation-metrics to add the current-period snapshot if the week is missing
  • Pass to /report:board-brief as a program-initiative input for the quarterly brief
  • Open an issue on the Next Targets list if the user wants to queue them as engineering work

Examples

# Current week, all frameworks
/report:automation-coverage

# Specific week
/report:automation-coverage 2026-W16

# SOC 2 and FedRAMP only
/report:automation-coverage 2026-W16 soc2,fedramp-moderate

Board Brief

Draft a quarterly board or audit-committee brief. This is a real board brief, not a bulleted slide outline. It uses prose where narrative carries meaning and tables where structure carries meaning. Every section is concise. Length budget: 2 pages for audit committee, 1 page for full board. Business impact first, control text last.

Arguments

  • $1 - Quarter (optional, defaults to current quarter, e.g. 2026-Q1)
  • $2 - Audience (optional: board, audit-committee, risk-committee, defaults to audit-committee)

Instructions

1. Context check

Invoke context-bootstrap. For a meaningful quarterly brief, check:

  • Findings cache has runs across the full quarter, not just the last week
  • Risk register at ./grc-data/risks/ with residual risk values, following docs/GRC-DATA.md
  • Incident history in ./grc-data/incidents/ (if tracked)
  • Framework coverage in scope - a board brief needs to name the frameworks the committee oversees

Partial context is acceptable here if the user confirms. A quarterly brief with limited data is a real artifact - just name the gaps.

2. Auto-discover

  • All findings runs within the quarter window
  • Residual risk totals, top 5 risks by score
  • Incidents logged in the quarter
  • Compliance trend: start-of-quarter coverage vs end-of-quarter coverage per framework

3. Ask for narrative context

  • Material events this quarter (incidents, audits, framework renewals, regulatory changes)
  • Decisions requested from the committee with the level of detail they want (one-line asks or full papers)
  • Strategic initiatives the CISO wants the committee to see (automation programs, org changes, budget)
  • Audience-specific framing - audit committee wants risk-and-assurance; full board wants strategy

4. Generate

Apply so-what-translation + exec-narrative-patterns + program-portfolio-composition for cross-framework synthesis.

Concision rules:

  • No paragraph longer than 3 sentences.
  • Tables for multi-framework posture and risk tracking. Prose for narrative sections (material events, initiatives).
  • Every open item has a named owner and a date. Anonymous ownership reads as no ownership.
  • Cut every sentence that doesn't move a decision.

Structure:

# <Audience> Brief - <Quarter>

## Headline

<One sentence. The most important thing the committee needs to walk away with.>

## Program Posture

<Short table: framework, coverage %, delta from last quarter, 1-line commentary.>

## Material Events

<Prose. 1-3 short paragraphs. Incidents, audits, regulatory changes, with business impact. No blow-by-blow.>

## Residual Risk

<Short table: top 5 risks, trend vs last quarter, treatment status, owner, expected close.>

## Program Initiatives

<Prose. 2-4 short paragraphs. Automation programs, org changes, tooling. What the CISO wants the committee to know and why it matters.>

## Asks

<Bulleted. Each ask: the decision, the context in one line, the deadline, the owner ready to execute.>

## Appendix

<Findings run IDs, gap reports, incident postmortems. Linked, not inlined.>

5. Save and offer next

Write to ./grc-reports/board-brief-<quarter>-<audience>.md. Offer:

  • PDF or DOCX via pandoc (most boards want a PDF)
  • Tighten into a 1-page board summary with a follow-on editing pass if the committee wants a shorter cut
  • Commit to grc-data/history/quarters/ for trend reference

Examples

# Current quarter, audit committee
/report:board-brief

# Specific quarter, full board
/report:board-brief 2026-Q1 board

# Risk committee version
/report:board-brief 2026-Q1 risk-committee

Exec Summary

Draft a weekly 1-page update for the CISO or direct leadership. Every section is bulleted and scannable. An exec should get the full picture in 60 seconds. Lead with wins and business impact, not control IDs.

Arguments

  • $1 - Period (optional, defaults to current week, e.g. 2026-W16)
  • $2 - Audience (optional: ciso, cio, ceo-weekly, defaults to ciso)

Instructions

1. Context check

Before drafting, verify the toolkit has what it needs. Invoke the context-bootstrap skill. Look for:

  • Findings cache populated: ls ~/.cache/claude-grc/findings/*/ returns recent runs
  • At least one framework plugin installed
  • Optional but recommended: ./grc-data/risks/ and ./grc-data/metrics/ following docs/GRC-DATA.md

If context is empty or partial, follow the context-bootstrap skill's setup path. Do not generate a hollow report.

2. Auto-discover

When context is complete, load without asking:

  • Most recent findings run per source
  • Risk register deltas from the last 7 days (new risks, closed risks, severity changes)
  • Open incidents from ./grc-data/incidents/ if the directory exists

3. Ask for narrative context

Ask the user for what Claude cannot infer:

  • Wins this week - automations shipped, controls closed, audits passed, programs launched. This is where GRC engineers show their work. If the user says "nothing" push once: closing even one finding is a win worth naming.
  • Material events this week (incidents, new regulatory hits, customer escalations) - paste bullets or say "none"
  • Leadership asks - decisions you need from the audience, budget requests, or "none"
  • Audience-specific framing - if $2 is ceo-weekly, confirm whether to include board-facing language

Skip questions the args already answered.

4. Generate

Apply the so-what-translation skill to translate findings into business impact. Apply exec-narrative-patterns for audience tone.

Every section is bulleted. No paragraphs. No hedging. Each bullet is one line, scannable at a glance.

Structure:

# Weekly Brief - <period>

Audience: <audience>

## Headline

- <One line. What changed this week that leadership should know.>

## Wins

- <Automation shipped, control closed, audit passed. Who drove it. Business impact.>
- <...>

## What Moved

- <Business-impact framing of top changes. Control IDs in the appendix, not here.>
- <...>

## Blockers

- <Open issues that need a decision, budget, or access. Named owner, specific ask.>
- <...>

## Asks

- <Specific decision requested. Context in one line. Deadline.>
- <...>

## Appendix

- Findings run: `<run_id>`
- Frameworks covered: `<list>`
- Full gap report: `<path>`

5. Save and offer next

Write to ./grc-reports/exec-summary-<period>.md. Confirm path. Offer:

  • PDF render via pandoc if installed
  • Pass to /report:board-brief if this week's content feeds a quarterly draft
  • Commit to grc-data/history/ for trend analysis

Examples

# Current week, default audience
/report:exec-summary

# Specific week
/report:exec-summary 2026-W16

# Write for CEO weekly review
/report:exec-summary 2026-W16 ceo-weekly

Program Health

Draft a portfolio snapshot of the whole GRC program. Built for CISO 1:1s and program reviews, not for audit evidence.

Arguments

  • $1 - As-of date (optional, defaults to today, e.g. 2026-04-18)
  • $2 - Frameworks (optional, comma-separated framework aliases accepted by /grc-engineer:gap-assessment; defaults to all frameworks with recent runs)

Instructions

1. Context check

Invoke context-bootstrap. Program-health needs:

  • At least two framework plugins installed
  • At least one successful gap-assessment run per framework in scope
  • Optional: ./grc-data/metrics/ for trend data

Without at least two frameworks, this command has no portfolio to report on. Suggest /grc-engineer:frameworks to discover what's available and install a second framework before proceeding.

2. Auto-discover

  • All framework plugins installed
  • Most recent gap-assessment coverage per framework
  • Trend: 30-day, 90-day coverage deltas if history allows
  • Shared controls across frameworks (SCF crosswalk helps here)

3. Ask for narrative context

  • Framework priority order - which frameworks the CISO cares about most this period
  • Any frameworks to exclude from the view (scoping changes, deprecations)
  • Known initiatives not yet reflected in findings (e.g., automation project landing next week)

4. Generate

Apply program-portfolio-composition for cross-framework synthesis. Apply so-what-translation for the commentary column.

Structure:

# Program Health - <as-of>

## Portfolio Snapshot
| Framework | Coverage | 30-day trend | Top gap | Owner |
|---|---|---|---|---|
| <framework> | <%> | <+/- pp> | <1-line gap> | <name or team> |

## Cross-Framework Patterns
<Controls that fail in multiple frameworks get called out here. SCF crosswalk shows the leverage points where one fix unblocks many.>

## Program Momentum
<What got better this period. What got worse. What's static and shouldn't be.>

## Watch List
<Frameworks or controls at risk of slipping without intervention.>

## Appendix
Per-framework full reports: <paths>
SCF crosswalk run: <run_id>

5. Save and offer next

Write to ./grc-reports/program-health-<as-of>.md. Offer:

  • Pass to /report:exec-summary for a weekly cut
  • Pass to /report:board-brief for a quarterly roll-up
  • PDF render via pandoc

Examples

# Today, all frameworks with runs
/report:program-health

# Specific date, specific frameworks
/report:program-health 2026-04-18 soc2,fedramp-moderate,iso27001

Sponsors

Details

Marketplace
GRCEngClub/claude-grc-engineering
Source
plugins/grc-reporter
Category
Community

More from GRCEngClub/claude-grc-engineering

All 70