audit-review-decisions

audit-review-decisions is a skill for Claude Code from TalonT-Org/AutoSkillit. It costs 84 tokens per session (3,081 once invoked), scanned A, original, MIT.

A review-debt audit tool that examines merged GitHub pull-request discussions for suggestions that were accepted or deferred but never completed. It classifies the findings as valid, resolved, or stale.

In plain words
What is it for?
Use it to find deferred review items, future work, and out-of-scope decisions across recent merged pull requests.
Why use it?
It helps recover follow-up work that can disappear after a pull request is merged, before deferred decisions become forgotten maintenance problems.

Skill for Claude Code

Written for Claude Code: hooks in frontmatter. Also seen: mentions subagents; positional $N argument.

Part of the autoskillit plugin — 121 skills, 1 MCP server shipped together

Good fit Use it to find deferred review items, future work, and out-of-scope decisions across recent merged pull requests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/talont-org/autoskillit/audit-review-decisions
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.

Any agent
npx skills add TalonT-Org/AutoSkillit --skill audit-review-decisions
Clone the repo
git clone --depth 1 https://github.com/TalonT-Org/AutoSkillit

Made for: Claude Code.

Or install autoskillit, the plugin that ships this one along with the rest of its 121 skills, 1 MCP server.

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-review-decisions

README.md
[![agentmods](https://agentmods.dev/badge/skills/talont-org/autoskillit/audit-review-decisions/github.svg)](https://agentmods.dev/skills/talont-org/autoskillit/audit-review-decisions)
Your own site
<a href="https://agentmods.dev/skills/talont-org/autoskillit/audit-review-decisions"><img src="https://agentmods.dev/badge/skills/talont-org/autoskillit/audit-review-decisions/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 audit-review-decisions

Your own site · 80×15
<a href="https://agentmods.dev/skills/talont-org/autoskillit/audit-review-decisions"><img src="https://agentmods.dev/badge/skills/talont-org/autoskillit/audit-review-decisions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,081 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 $0.00084 $0.03081
Opus 5 $0.00042 $0.01541
Sonnet 5 $0.00017 $0.00616
Haiku 4.5 $0.00008 $0.00308

Measured 10d ago against content hash 2d060a250263, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

audit-review-decisions 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 10d 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.

src/autoskillit/skills_extended/audit-review-decisions/SKILL.md · 329 lines

How it starts

The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Review Decisions Skill

Mine merged PR review threads for agreed-but-deferred suggestions that were never implemented. Identify review debt before it compounds.

When to Use

  • User says "audit review decisions", "find deferred review items", "surface review debt", "what did reviewers flag for later"

Arguments

  • $1 — Time period (e.g. 14d, 30d, 7d). Default: 14d.
  • $2 — Output path. Default: ${AUTOSKILLIT_TEMP}/audit-review-decisions/review_decisions_audit_$(date +%Y-%m-%d_%H%M%S).md

Critical Constraints

NEVER:

  • Create files outside ${AUTOSKILLIT_TEMP}/audit-review-decisions/
  • Have triage or validation subagents make GitHub API calls (local data only for Step 2)
  • Post duplicate [AUDIT] markers — check for existing marker before posting
  • Run subagents in the background (run_in_background: true is prohibited)
  • Use gh pr list without --limit to avoid pagination truncation
  • Use \| in Grep patterns — use | for alternation (ERE, not BRE)

ALWAYS:

  • Save raw PR JSON to temp before any analysis (Step 1)
  • Use GraphQL alias batching (~20 PRs per query) for data collection
  • Include rateLimit { cost remaining resetAt } in every GraphQL query
  • Sleep 1s between consecutive mutating GitHub API calls (Step 5 watermark posts)
  • Step 2 triage subagents read local JSON files only — zero API calls
  • Step 3 validation subagents grep the actual current codebase
  • Skip threads that already contain an [AUDIT] comment
  • Resolve owner/repo from git remote get-url origin — never hardcode
  • Use /autoskillit: prefix when invoking any other skill

Workflow

Step 0: Watermark Resolution

  1. Parse $1 for time period. Default 14d. Compute PERIOD_DAYS.

  2. Resolve OWNER and REPO from git remote get-url origin.

  3. Query the most recent [AUDIT] sentinel comment across recently merged PRs:

    gh api graphql -f query='
      query($owner:String!, $name:String!) {
        rateLimit { cost remaining resetAt }
        repository(owner:$owner, name:$name) {
          pullRequests(first:500, states:MERGED, orderBy:{field:UPDATED_AT,direction:DESC}) {
            nodes { number
              reviewThreads(first:50) {
                nodes { comments(first:10) { nodes { body createdAt } } }
              }
            }
          }
        }
      }' -f owner="${OWNER}" -f name="${REPO}"
    

    Extract the most recent createdAt from any comment whose body starts with [AUDIT]. Store as LAST_AUDIT_TS (empty string if none — first run).

Read the full file on GitHub · 329 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. 10d ago First seen · 329 lines · 84 tokens per session scan A 2d060a250263

Subscribe to this mod's changes

audit-review-decisions is a skill published in the GitHub repository TalonT-Org/AutoSkillit (5 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 3,081 once invoked, about $0.0004 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 2026-08-31.

Related

Other skills, from other repositories

agent-review

Critically review a Stencila agent and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve an agent directory or AGENT.md file. Covers frontmatter validation, system instruction quality, configuration correctness, and adherence to the Agent schema.

stencila/stencila · 57 tokens

pr

Use when reviewing an incoming GitHub pull request — runs the multi-level (L1-L5) audit against the PR's real diff range, posts findings as one batched review (inline, summary, or local-only), offers the standard fix chain on NEEDSFIX, and optionally merges. The maintainer-side counterpart to /hyperflow:issue. Trigger…

jeremylongshore/tons-of-skills-marketplace · 105 tokens

代码审查员

A code-review agent that examines changes for correctness, security, maintainability, performance, and test coverage.

KongFangXun/sofagent · 40 tokens

laravel-audit

Perform a deep, structured, evidence-based audit of a Laravel application and produce actionable findings backed by concrete project evidence. Use when asked to audit, review, assess, or evaluate an existing Laravel codebase.

MrPunyapal/laravel-auditor · 46 tokens

laravel-audit-dsa

Run a read-only, orchestrated audit of a Laravel codebase for data structures, state representation, algorithms, and ownership. Use when asked for a DSA audit, subsystem inventory, or Aaron-style bounded agent audit.

MrPunyapal/laravel-auditor · 51 tokens

audit-expert

Expert-level security auditing, compliance, code review, and vulnerability assessment. Use when the user mentions compliance, security review, code review, vulnerability assessment, SOC 2, or GDPR, or when the task involves Audit Types, Audit Frameworks, Audit Process, or Authentication Review.

personamanagmentlayer/pcl · 60 tokens