review-narrative

review-narrative is a command for Claude Code from mlunato47/claude-grc-plugin. It costs 9 tokens per session (1,396 once invoked), scanned A, original, MIT.

A review command for checking whether a written explanation of how a security control is implemented is complete and well supported. A control is a required security or compliance practice, identified by a framework and control ID.

In plain words
What is it for?
Use it to review implementation narratives for frameworks such as NIST, FedRAMP, CMMC, SOC 2, ISO 27001, PCI, HIPAA, or CIS.
Why use it?
It helps find missing details and quality problems before the narrative is used in an audit or assessment.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the grc plugin — 1 skill, 24 commands shipped together

Good fit Use it to review implementation narratives for frameworks such as NIST, FedRAMP, CMMC, SOC 2, ISO 27001, PCI, HIPAA, or CIS.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/mlunato47/claude-grc-plugin/review-narrative
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/mlunato47/claude-grc-plugin

Made for: Claude Code.

Or install grc, the plugin that ships this one along with the rest of its 1 skill, 24 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for review-narrative

README.md
[![agentmods](https://agentmods.dev/badge/commands/mlunato47/claude-grc-plugin/review-narrative/github.svg)](https://agentmods.dev/commands/mlunato47/claude-grc-plugin/review-narrative)
Your own site
<a href="https://agentmods.dev/commands/mlunato47/claude-grc-plugin/review-narrative"><img src="https://agentmods.dev/badge/commands/mlunato47/claude-grc-plugin/review-narrative/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review-narrative

Your own site · 80×15
<a href="https://agentmods.dev/commands/mlunato47/claude-grc-plugin/review-narrative"><img src="https://agentmods.dev/badge/commands/mlunato47/claude-grc-plugin/review-narrative.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,396 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00009 $0.01396
Opus 5 $0.00005 $0.00698
Sonnet 5 $0.00002 $0.00279
Haiku 4.5 $0.00001 $0.00140

Measured 9d ago against content hash 6659cd3a74e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

review-narrative scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

grc/commands/review-narrative.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/grc:review-narrative

Review a control implementation narrative for completeness and quality.

Usage

/grc:review-narrative [framework] [control-id] [baseline?]

The user pastes their narrative text after invoking the command, or includes it as part of the prompt.

Arguments

  • framework: The compliance framework. Accepts: nist, fedramp, fisma, cmmc, soc2, iso27001, pci, hipaa, cis
  • control-id: The specific control ID (e.g., ac-2, ia-2, sc-7)
  • baseline (optional): low, moderate, high. Defaults to moderate for NIST/FedRAMP.

Examples

/grc:review-narrative fedramp ac-2
/grc:review-narrative fedramp ac-2 high
/grc:review-narrative nist ia-2 moderate
/grc:review-narrative cmmc 3.5.3

Behavior

When invoked:

  1. Display the Data Sensitivity Notice at the top of every response (see SKILL.md Data Handling section).

  2. Read the appropriate reference files:

    • Framework file from skills/grc-knowledge/frameworks/ for control details and ODP values
    • skills/grc-knowledge/audits/narrative-quality-criteria.md for scoring rubric
    • Mapping files if cross-framework context is helpful
  3. Evaluate the narrative against these criteria:

    a. Five W's Completeness For each element (What, Who, How, When, Where), determine if it is:

    • Present: Clearly addressed with specifics
    • Partial: Mentioned but vague or incomplete
    • Missing: Not addressed at all

    b. ODP/Parameter Check For each organization-defined parameter required by the control:

    • State what the parameter requires
    • Note the FedRAMP-required value (if FedRAMP framework and value is mandated)
    • State what value was found in the narrative (or "Not specified")
    • Flag mismatches with framework-required values

    c. Enhancement Coverage For each enhancement applicable at the stated baseline:

    • State whether it is Addressed, Partially Addressed, or Not Addressed in the narrative
    • Note what's missing for partially addressed enhancements

Read the full file on GitHub · 138 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 138 lines · 9 tokens per session scan A 6659cd3a74e6

Subscribe to this mod's changes

review-narrative is a command published in the GitHub repository mlunato47/claude-grc-plugin (181 stars, last pushed 1mo ago), licensed MIT. It adds 9 tokens to every session and 1,396 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.