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.
npx agentmods add skills/cookys/autopilot/l3npx skills add cookys/autopilot --skill l3git clone --depth 1 https://github.com/cookys/autopilotWrote 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/l3)<a href="https://agentmods.dev/skills/cookys/autopilot/l3"><img src="https://agentmods.dev/badge/skills/cookys/autopilot/l3.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 | $0.00136 | $0.00976 |
| Opus 5 | $0.00068 | $0.00488 |
| Sonnet 5 | $0.00027 | $0.00195 |
| Haiku 4.5 | $0.00014 | $0.00098 |
Grade A, and why
l3 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex lifecycle adapter (normative override)
This section overrides any later host-specific lifecycle or dispatch spelling in the canonical skill
body. Resolve <plugin-root> as the installed Autopilot plugin directory that contains this skill.
When using the packaged managed CLI, enter through the existing explicit marker command:
node "<plugin-root>/scripts/session-mode.js" set --level <l3|l4|l5|l6> --entry-level <requested-level> --repo-root <git-root>
The production Codex package currently registers only its PostCompact recovery hook. It does not
ship a Codex-thread-bound PreToolUse direct-mutation gate, and this shell command must not be
described as receiving or exporting a CODEX_THREAD_ID binding. The marker is an explicit
CLI/Engine admission artifact; it is not a production hook admission proof. A marker from another
explicitly bound session is not reusable when the managed CLI validates it.
Continue only when the emitted marker contains mission_routing.status: "READY", admitted: true, and
would_block: false. Managed implementation then follows the existing Mission admission, sealed
campaign, and AUTOPILOT_LEVEL=<level> node "<plugin-root>/bin/autopilot.js" engine implement-review ...
route. Repairs attach to and resume that same engine/campaign lineage. A Codex implementer launched
inside that route receives a credentials-only isolated CODEX_HOME, never the controller plugin or
configuration.
Codex in this package does not provide TaskCreate, TaskUpdate, TaskStop, native Agent, or
subagent_type. Do not imitate them with Markdown tickets, inline managed implementation, a new
branch/session, or a replacement graph. If an exact mapping is unavailable, stop with the existing
precondition or abort receipt; do not invent another lifecycle authority.
/l3 — CEO autonomy, inline
Routing overlap? If this intent better matches a sibling skill, redirect per references/routing-tiebreaks.md (prefer explicit commands over conversational autonomy).
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.
- 4d ago First seen · 68 lines · 136 tokens per session scan A 321698125275
l3 is a skill published in the GitHub repository cookys/autopilot (11 stars, last pushed 4d ago), licensed MIT. It adds 136 tokens to every session and 976 once invoked, about $0.0007 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.
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.
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.
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.
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.
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…