audit-restore

audit-restore is a command for coding agents from sergei-aronsen/claude-code-toolkit. It costs 0 tokens per session (2,441 once invoked), scanned A, original, MIT.

A command that removes one previously allowed audit exception from the project's exception list. An exception tells an audit tool to ignore a known finding.

In plain words
What is it for?
Use it with a file location and rule name to restore a security or other audit finding, after reviewing the full exception and confirming its removal.
Why use it?
It lets you put a finding back under review when a refactor makes it relevant again or the original reason for ignoring it no longer applies.

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/sergei-aronsen/claude-code-toolkit/audit-restore
Clone the repo
git clone --depth 1 https://github.com/sergei-aronsen/claude-code-toolkit

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 audit-restore

README.md
[![agentmods](https://agentmods.dev/badge/commands/sergei-aronsen/claude-code-toolkit/audit-restore.svg)](https://agentmods.dev/commands/sergei-aronsen/claude-code-toolkit/audit-restore)
Your own site
<a href="https://agentmods.dev/commands/sergei-aronsen/claude-code-toolkit/audit-restore"><img src="https://agentmods.dev/badge/commands/sergei-aronsen/claude-code-toolkit/audit-restore.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,441 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.02441
Opus 5 $0.00000 $0.01221
Sonnet 5 $0.00000 $0.00488
Haiku 4.5 $0.00000 $0.00244

Measured 5d ago against content hash 847afbe4b72d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-restore scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

piped/curl context (per CONTEXT.md "Established Patterns"). Fall back to plain `read` from
commands/audit-restore.md · 264 lines

How it starts

The opening of the file, as written. The whole thing — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/audit-restore — Remove a False-Positive Exception from the Allowlist

Purpose

Remove an entry from .claude/rules/audit-exceptions.md when an exception turns out to be a real bug — for example, after a refactor changes the threat model or the Council pass (/council audit-review) marks a previously-suppressed finding disputed.

Removal is guarded by an interactive [y/N] prompt that defaults to NO. The full entry block is displayed before the prompt so the user sees exactly what will be deleted.


Usage

/audit-restore <file:line> <rule>

Examples:

  • /audit-restore src/foo.ts:42 SEC-XSS
  • /audit-restore scripts/setup-security.sh:142 SEC-RAW-EXEC

When to Use

  • After a refactor changes the data flow that justified the original exception.
  • After a Council audit-review pass returns disputed for a previously-suppressed entry.
  • When the rule itself is removed from the auditor's rule set (the entry is now meaningless).
  • DO NOT use to "shut up" a stale exception you don't understand — read the original Reason field first; if the Reason no longer applies, that's a sign you genuinely want to restore.

Process

Step 1 — Parse Arguments

Parse the two required positional tokens: <file:line> and <rule>. No reason argument, no flags beyond the two positional tokens.

set -euo pipefail

ARGS=("$@")
if [ "${#ARGS[@]}" -ne 2 ]; then
    printf 'audit-restore: usage: /audit-restore <file:line> <rule>\n' >&2
    exit 2
fi

FILE_LINE="${ARGS[0]}"
RULE="${ARGS[1]}"

PATH_PART="${FILE_LINE%:*}"
LINE_PART="${FILE_LINE##*:}"

case "$LINE_PART" in
    ''|*[!0-9]*)
        printf 'audit-restore: <file:line> must end with :<positive integer>, got %q\n' "$FILE_LINE" >&2
        exit 2
        ;;
esac

EXC_FILE=".claude/rules/audit-exceptions.md"
HEADING="### ${PATH_PART}:${LINE_PART} — ${RULE}"

The em-dash in the HEADING string is a literal U+2014 character . Type it directly — do not escape as &mdash; or &#8212;.

Read the full file on GitHub · 264 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. 5d ago First seen · 264 lines · 0 tokens per session scan A 847afbe4b72d

Subscribe to this mod's changes

audit-restore is a command published in the GitHub repository sergei-aronsen/claude-code-toolkit (5 stars, last pushed 19d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,441 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.