deviation-request

A compliance-writing tool for drafting requests to temporarily depart from a security requirement, accept a risk, or explain why a scanner finding is incorrect.

In plain words
What is it for?
Use it to prepare deviation requests for operational limits, false positives, compensating controls, vendor dependencies, technology constraints, or temporary exceptions.
Why use it?
It helps document why a control cannot be fully met or why a finding should not be remediated as reported.

Command

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.

agentmods
npx agentmods add commands/mlunato47/claude-grc-plugin/deviation-request
Clone the repo
git clone --depth 1 https://github.com/mlunato47/claude-grc-plugin
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,011 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00013 $0.01011
Opus 5 $0.00006 $0.00505
Sonnet 5 $0.00003 $0.00202
Haiku 4.5 $0.00001 $0.00101

Measured 2d ago against content hash ca63b59f90ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deviation-request 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 2d 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/deviation-request.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/grc:deviation-request

Draft deviation requests, risk acceptances, or false positive justifications.

Usage

/grc:deviation-request [framework] [control-id] [reason-type]

Arguments

  • framework: The compliance framework
  • control-id: The specific control ID requiring deviation
  • reason-type: The type of deviation. Accepts:
    • operational — Operational requirement prevents full implementation
    • false-positive — Scanner finding is a false positive
    • risk-adjustment — Risk is mitigated by compensating controls
    • vendor-dependency — Remediation depends on vendor action
    • technology-constraint — Technical limitation prevents implementation
    • temporary — Temporary deviation with planned remediation

Examples

/grc:deviation-request fedramp si-2 vendor-dependency
/grc:deviation-request fedramp ac-7 operational
/grc:deviation-request pci 6.3.3 false-positive
/grc:deviation-request nist sc-28 technology-constraint
/grc:deviation-request fedramp ra-5 temporary

Behavior

When invoked:

  1. Identify the framework, control, and reason type from arguments.

  2. Read the relevant framework reference and POA&M management reference (conmon/poam-management.md).

  3. Draft a deviation request that includes all required elements:

    a. Finding identification:

    • POA&M ID / Weakness ID
    • Control ID and title
    • Finding source (scan tool, assessment, etc.)
    • Original severity and risk rating

    b. Deviation justification (varies by reason type):

    • Operational: Why the control cannot be fully implemented, what business process depends on the exception, impact of full implementation
    • False positive: Technical evidence that the finding is not a true vulnerability, scanner configuration details, manual verification results
    • Risk adjustment: Compensating controls in place, residual risk calculation, why compensating controls adequately mitigate the risk
    • Vendor dependency: Vendor ticket/case number, vendor acknowledgment, expected vendor timeline, interim mitigations
    • Technology constraint: Technical limitation details, alternatives evaluated, compensating controls
    • Temporary: Planned remediation date, milestones, interim mitigations

Read the full file on GitHub · 126 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. 2d ago First seen · 126 lines · 13 tokens per session scan A ca63b59f90ba

Subscribe to this mod's changes

deviation-request is a command published in the GitHub repository mlunato47/claude-grc-plugin (180 stars, last pushed 29d ago), licensed MIT. It adds 13 tokens to every session and 1,011 once invoked, about $0.0001 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.