engine-onboarding

A qualification process for testing whether a new AI model or execution system is suitable for specific coding-work roles.

In plain words
What is it for?
It helps test, score, approve, route, and later re-check models for defined roles and task scopes using recorded qualification evidence.
Why use it?
A model that performs well in one role may not be reliable as a planner, implementer, reviewer, or verifier.

Skill for Claude CodeCodex

Part of the autopilot plugin — 32 skills, 3 agents, 7 hooks shipped together

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/cookys/autopilot/engine-onboarding
Any agent
npx skills add cookys/autopilot --skill engine-onboarding
Clone the repo
git clone --depth 1 https://github.com/cookys/autopilot

Made for: Claude Code, Codex.

Or install autopilot, the plugin that ships this one along with the rest of its 32 skills, 3 agents, 7 hooks.

Per session 155 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,741 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 $0.00155 $0.04741
Opus 5 $0.00077 $0.02371
Sonnet 5 $0.00031 $0.00948
Haiku 4.5 $0.00015 $0.00474

Measured 3d ago against content hash 3d18ce2b7996, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

engine-onboarding 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 3d 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.

platforms/codex/plugin/skills/engine-onboarding/SKILL.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Engine Onboarding (heterogeneous lifecycle)

Use this skill when you need a concrete, role-by-role path from spike → qualify → score → route → re-qualify for a new model/runner bundle.

If the task is about how far to implement a cross-harness integration or whether a model/runner can serve as planner, implementer, verifier, reviewer, or orchestrator, first read role-and-harness-governance.md. Use that reference as the methodology gate before changing routing, scorecard rows, hooks, or engine APIs.

Current scope

Reviewer, owner, and brain-seat end-to-end qualification are shipped gate paths today (brain = the 勤勞×公平×收斂 standing exam; one atomic owner-brain-seat-v1 record on the owner role with forced brain-seat scope, no expiry, 3-strike revocation via engine-capability-state.js brain-status).

  • stage-0 spike and exact-scope stage-1 reviewer/owner qualification are implemented with separate repeated nonce-derived corpora, host oracles, and executable mutation controls.
  • ✅ Qualification evidence is keyed by exact role, task/domain/language/tool scope and deployment identity; legacy scorecard rows remain compatibility-only.
  • ✅ Canonical roles are owner, implementer, reviewer, verification_author, and explorer. Scorecard input aliases planner/orchestrator to owner and verifier to reviewer; stored and returned rows are canonical.
  • ⚠️ Explorer auto-qualification still requires its own role-specific eval suite before autonomous routing; reviewer, owner, brain, verification_author, and implementer suites are shipped (engine-qualify.sh <role>). The implementer suite is live-rail (real dispatch-hetero.sh, 6 families × 2 trials; plan docs/plans/2026-08-22-implementer-qualification-suite.md), unlike the broker-based reviewer/owner/brain/VA suites.
  • ⚠️ Local OpenAI-compatible transport is available only after a deployment's semantic and operational identity can be bound. A configured label or API response alone is not qualification.

Read the full file on GitHub · 251 lines

Files

What ships with it

1 file 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. 3d ago First seen · 251 lines · 155 tokens per session scan A 3d18ce2b7996

Subscribe to this mod's changes

engine-onboarding is a skill published in the GitHub repository cookys/autopilot (11 stars, last pushed 3d ago), licensed MIT. It adds 155 tokens to every session and 4,741 once invoked, about $0.0008 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.

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