audit

A read-only review of project documentation against the actual codebase. It checks whether documents are complete, consistent, accurate, and still match the software.

In plain words
What is it for?
Use it to review guides, API documentation, architecture notes, and other project documents, with findings ranked by severity.
Why use it?
It finds outdated instructions, missing coverage, contradictions, and misleading technical information before they cause confusion or errors.

Skill for Claude CodeCodex

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 skills/tercel/spec-forge/audit
Any agent
npx skills add tercel/spec-forge --skill audit
Clone the repo
git clone --depth 1 https://github.com/tercel/spec-forge

Made for: Claude Code, Codex.

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,078 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 $0.00063 $0.03078
Opus 5 $0.00032 $0.01539
Sonnet 5 $0.00013 $0.00616
Haiku 4.5 $0.00006 $0.00308

Measured 2d ago against content hash aabeb17997e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit 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.

skills/audit/SKILL.md · 304 lines

How it starts

The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit — Documentation Quality & Consistency Review

Systematically review existing project documentation for quality, completeness, consistency with code, and internal coherence. Produce a prioritized findings report.

Core Principles

  1. Evidence-based: Every finding must cite a specific file, section, or line — no vague complaints
  2. Code-grounded: Cross-reference documentation claims against the actual codebase
  3. Prioritized: Findings are classified by severity so the user can fix what matters first
  4. Read-only by default: This skill only reads and reports — document modifications require explicit user opt-in (Step 8)
  5. Honest: Report real issues, don't inflate findings to look thorough

Severity Levels

Severity Meaning Example
Critical Documentation is wrong or dangerously misleading API doc shows deleted endpoint, security guide has incorrect auth flow
Major Significant gap or inconsistency that causes confusion Feature doc missing for a core module, conflicting architecture descriptions
Minor Quality issue that degrades usefulness but isn't blocking Typos in API params, outdated version numbers, missing examples
Info Observation or improvement suggestion Better organization possible, diagram would help clarity

Workflow

Step 1: Determine Audit Scope

Parse the arguments to determine what to audit:

  1. If a path argument is provided (e.g., /spec-forge:audit ../../other-project), use that as the project root
  2. If no path, use the current working directory
  3. Verify the target has documentation (check for docs/, README.md, or markdown files)

If no documentation found, inform the user and stop.

Use AskUserQuestion to ask:

  • Audit focus: Full audit, or focus on a specific area? (Options: Full / API docs only / Feature docs only / Architecture docs only / Custom path)
  • Code alignment: Should I cross-reference docs against the codebase? (Yes / No — skip if docs-only repo like aipartnerup-docs)

Read the full file on GitHub · 304 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 · 304 lines · 63 tokens per session scan A aabeb17997e0

Subscribe to this mod's changes

audit is a skill published in the GitHub repository tercel/spec-forge (5 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 3,078 once invoked, about $0.0003 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

ppt-design-skill

Design, generate, review, and revise editable PowerPoint presentations through a rigorous brief-to-PNG workflow using the public pptx-designer Python library.

sunchaokun/PPT-Design-Skill · 35 tokens

manager

Sync session work into GitHub issues, or query track status across repos. Write: find/update issue + W-label. Read: "что по ". Triggers: "создай issue", "синкни сессию", "manager". Not day/week plans (daily-tasks).

serejaris/personal-corp-os · 63 tokens

weekly-retro

Use when the user is closing an ISO week, reviewing planned outcomes against evidence, interviewing work Areas, resolving unfinished commitments, or asking for "ретро", "weekly retro", "week review", or lessons from the week.

serejaris/personal-corp-os · 49 tokens

art-director

Orchestrate iterative visual style searches with branch prompts, decision graphs, feedback loops, and final direction selection.

serejaris/personal-corp-os · 26 tokens

corp-doctor

Use when a Personal Corp operating loop needs setup, repair, a new department, or task routing: HQ files and agent rules, GitHub issue workflow, corp- owner map, department repositories, or deciding which repo an issue belongs to. Triggers: "corp doctor", "почини контур", "заведи отдел", "куда положить задачу"…

serejaris/personal-corp-os · 102 tokens

html-draft

Use when user wants a standalone HTML diagram in flat engineering blueprint style — architecture diagrams, system flows, technical spec sheets, component maps. Generates one HTML file using Tailwind v4 (browser CDN) for layout and D3 v7 (CDN) for SVG diagrams. User-invoked only — do NOT auto-trigger. Triggers on…

serejaris/personal-corp-os · 130 tokens