Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/cookys/autopilotnpx agentmods add skills/cookys/autopilot/harness-maintenanceWrote 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.
[](https://agentmods.dev/skills/cookys/autopilot/harness-maintenance)<a href="https://agentmods.dev/skills/cookys/autopilot/harness-maintenance"><img src="https://agentmods.dev/badge/skills/cookys/autopilot/harness-maintenance.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00079 | $0.00767 |
| Opus 5 | $0.00039 | $0.00383 |
| Sonnet 5 | $0.00016 | $0.00153 |
| Haiku 4.5 | $0.00008 | $0.00077 |
Grade A, and why
harness-maintenance 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Maintenance
Use this skill to keep fast-moving harness facts out of memory and out of engine code.
Start Here
Run the read-only capability report first:
node bin/autopilot.js harness report --stale-after 14d
For a bounded SessionStart-style warning:
node bin/autopilot.js harness report --stale-after 14d --required-level H3 --format warning
If any target harness is stale, unverified, warning, unavailable, or below the required harness level, do not implement H3+ dispatch, hooks, gating, or orchestration from memory. Run a survey or local spike first.
Available Scripts
| Script | Use |
|---|---|
scripts/measure-profile-context.js |
Produce content-free source, rule-inventory, or persisted Codex context summaries. A byte estimate is conservative evidence only; it cannot prove an exact-token budget or another host's prompt visibility. |
scripts/probe-skill-frontmatter-portability.sh |
Run disposable Claude Code/Codex skill-load probes and emit a version-bound pass/fail/inconclusive receipt before changing frontmatter metadata. |
scripts/probe-harness-capabilities.sh |
Re-probe the exact platform surfaces consumed by the capability-trigger mission and delegate the closed aggregate receipt write to the canonical claim validator. |
scripts/platform-capability-claims.js |
Generate and immediately revalidate content-addressed capability claims plus the exact D2/D3/D4 consumer partition. Only this script emits validated claim IDs. |
scripts/probe-todo-tools-pin.js |
Single live-call probe: do the task tools (TaskCreate family) reach a headless session from this directory's environment? Run after touching settings/env wiring; --expect-absent is the planted-red arm. Exit 0 met / 1 contradicted / 2 indeterminate. |
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 · 60 lines · 79 tokens per session scan A eeb4ea913798
harness-maintenance is a skill published in the GitHub repository cookys/autopilot (11 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 767 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…