A user-facing command for auditing whether a coding plan was implemented in the codebase. It uses the plan's base revision—the earlier code state—to determine which changes belong to the plan and reports the auditor's findings.

Use it to audit a completed plan from its path and receive a report about what was implemented.

It provides a separate completion check when you want to verify a plan without changing its status. This helps reveal missing work or differences between the plan and the final code.

c-audit — Skill for Claude Code by sentasity

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add sentasity/cadence

Claude Code

/plugin install cadence

Made for: Claude Code.

Or install cadence, the plugin that ships this one along with the rest of its 11 skills, 5 agents, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sentasity/cadence/c-audit.svg)](https://agentmods.dev/skills/sentasity/cadence/c-audit)

Your own site

<a href="https://agentmods.dev/skills/sentasity/cadence/c-audit"><img src="https://agentmods.dev/badge/skills/sentasity/cadence/c-audit.svg" alt="Measured on agentmods" height="20"></a>

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,119 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.

Model	Per session	Once invoked
Fable 5.1	$0.00104	$0.02119
Opus 5	$0.00052	$0.01059
Sonnet 5	$0.00021	$0.00424
Haiku 4.5	$0.00010	$0.00212

Measured 7d ago against content hash efac4c6693c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

c-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 7d 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/c-audit/SKILL.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

`/c-audit`

You verify a plan was actually implemented. You delegate the heavy lifting to the cadence-completion-auditor agent (which orchestrates per-audit sub-agents); your job is pre-flight, invocation, and surfacing the agent's report to the user.

Architecture: standalone wrapper around the auditor agent

This skill is the standalone invocation path. /c-execute does NOT route its completion-gate audit through this skill — it dispatches cadence-completion-auditor directly. The agent is the single source of truth for audit logic; both invocation paths (this skill, and /c-execute's gating call) dispatch the same agent with the same parameters and produce identical results.

This means: if you ever change audit behavior, change the agent. Changing this skill only affects the standalone UX (pre-flight messages, output formatting).

Invocation form

/c-audit <plan-path> — standalone. Report only; do NOT flip status. There is no "called internally by /c-execute" mode — /c-execute doesn't call this skill, it dispatches the agent directly.

Pre-flight (in order)

Plan artifact exists — resolve the plan slug via skills/_shared/storage-resolution.md (resolve); it must have an 00-overview.
Linked design exists. Read the plan overview via skills/_shared/storage-resolution.md (read_artifact), then resolve the linked design (resolve) and confirm it exists with status: approved or later — do not read a raw linked_design: frontmatter line or assume a design folder path.
base_sha: is set. Read it from the plan overview via skills/_shared/storage-resolution.md (read_artifact). If missing:
- Abort with: "base_sha is not set on this plan's overview. /c-execute should have set it on first invocation. Either re-invoke /c-execute (which records base_sha) or manually set base_sha to the SHA at which execution started."
Diff range computable. git diff <base_sha>..HEAD should not error. If it does (e.g. base_sha not in current branch's history), surface the git error verbatim.

Read the full file on GitHub · 113 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.

7d ago First seen · 113 lines · 104 tokens per session scan A efac4c6693c2

Subscribe to this mod's changes

c-audit is a skill published in the GitHub repository sentasity/cadence (1 stars, last pushed 12d ago), licensed MIT. It adds 104 tokens to every session and 2,119 once invoked, about $0.0005 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.

Claude Code Code review ai-agents claude-code-plugin developer-tools workflow

self-audit

Self-audit this skills repo against CLAUDE.md invariants, the artifact contract, and README/CLAUDE.md/docs sync via three parallel read-only subagents. Local meta-skill — independent of the /task: pipeline.

SpaiR/task-pipeline · 52 tokens

procoder

Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…

azrtydxb/procoder · 101 tokens

code-review

The depth half of a review - the dimensions a diff is read against (correctness, boundaries, concurrency, failure paths, secrets, data access, structure, test quality) and the rule that a finding is refuted before it is reported. The verdict stays with the reviewer agent. Use when reviewing a diff or a pull request…

jjanczur/tyran · 80 tokens

deslop

The optimization pass, defined - delete before you add, one smell class per pass, behaviour pinned by a test that ran BEFORE the edit. Lints a SKILL.md and prose by the same instinct. Use for the per-story optimization pass or when code has grown noisy without growing capable.

jjanczur/tyran · 58 tokens

loop-test

A local experiment for designing repeating checks with Claude Code’s loop command. It covers both fixed intervals and checks that schedule themselves again after each run.

restarter/lets-workflow · 112 tokens

take-task

A workflow for claiming a tracker task and preparing the development branch for it. It verifies the task, marks it as in progress, checks for uncommitted changes, and handles branch setup according to the task state.

restarter/lets-workflow · 76 tokens