audit-autopilot

audit-autopilot is a skill for Claude Code, Codex from MatthewYe/opencode-toolbox. It costs 87 tokens per session (1,503 once invoked), scanned A, original, MIT.

A post-run audit skill for checking how faithfully an autopilot coding workflow followed its agreement and plan.

In plain words
What is it for?
Use it after an autopilot run to evaluate execution quality, trace errors to session records, and produce a structured scorecard.
Why use it?
It uses OpenCode session traces to reveal mistakes, workflow friction, and departures from the requested process with evidence.

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/matthewye/opencode-toolbox/audit-autopilot
Any agent
npx skills add MatthewYe/opencode-toolbox --skill audit-autopilot
Clone the repo
git clone --depth 1 https://github.com/MatthewYe/opencode-toolbox

Made for: Claude Code, Codex.

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-autopilot

README.md
[![agentmods](https://agentmods.dev/badge/skills/matthewye/opencode-toolbox/audit-autopilot.svg)](https://agentmods.dev/skills/matthewye/opencode-toolbox/audit-autopilot)
Your own site
<a href="https://agentmods.dev/skills/matthewye/opencode-toolbox/audit-autopilot"><img src="https://agentmods.dev/badge/skills/matthewye/opencode-toolbox/audit-autopilot.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,503 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 $0.00087 $0.01503
Opus 5 $0.00044 $0.00751
Sonnet 5 $0.00017 $0.00301
Haiku 4.5 $0.00009 $0.00150

Measured 4d ago against content hash f66b4fce2a78, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-autopilot 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 4d 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-autopilot/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Autopilot

Audit an autopilot execution by analyzing its OpenCode session trace. The audit evaluates three layers of fidelity, producing a structured scorecard with evidence anchors back to the raw session data.

When to use

Run after an /autopilot session completes. User provides the orchestrator session ID (find it with opencode session list). Do not use for non-autopilot sessions.

Workflow

Step 0: Gather inputs

The session ID may come from the command argument (/audit-autopilot <session-id>) or be stated directly in the user's prompt. If already provided, skip asking and proceed.

If not provided, ask the user for:

  • Orchestrator session ID (required) — the session where /autopilot was invoked
  • Project directory (optional, defaults to cwd) — where .scratch/ issues and contracts live

If the user doesn't know the session ID, help them find it:

opencode session list --format json

Look for sessions with titles matching autopilot invocations or issue names.

If the user has already specified subagent session IDs or contract file paths, use them directly rather than re-discovering them.

Step 1: Export and parse sessions

Export the orchestrator session:

opencode export <session-id> > /tmp/audit-orchestrator.json

Parse this JSON to extract key metadata:

  • Issue sources: Find paths like .scratch/<feature>/issues/<NN-slug>/ or GitHub issue numbers in the user's initial messages
  • Subagent session IDs: Scan all task tool calls — each one has state.metadata.sessionId giving the child session ID. Track which session mapped to which agent type (implementer / reviewer) and round number
  • Contract files: From the orchestrator's dispatch prompts, locate AGENT-BRIEF.md and issue.md paths

For GitHub issues, the contract is embedded in the orchestrator's prompt text — extract it directly.

If the user already specified subagent session IDs, skip the discovery step and use the provided IDs directly. Export each subagent session:

opencode export <sub-session-id> > /tmp/audit-<agent>-r<round>.json

Read the full file on GitHub · 110 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 110 lines · 87 tokens per session scan A f66b4fce2a78

Subscribe to this mod's changes

audit-autopilot is a skill published in the GitHub repository MatthewYe/opencode-toolbox (5 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 1,503 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens