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/dormstern/forge/autonomy-tiersnpx skills add dormstern/forge --skill autonomy-tiersgit clone --depth 1 https://github.com/dormstern/forgeWrote 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/dormstern/forge/autonomy-tiers)<a href="https://agentmods.dev/skills/dormstern/forge/autonomy-tiers"><img src="https://agentmods.dev/badge/skills/dormstern/forge/autonomy-tiers.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 | $0.00102 | $0.01096 |
| Opus 5 | $0.00051 | $0.00548 |
| Sonnet 5 | $0.00020 | $0.00219 |
| Haiku 4.5 | $0.00010 | $0.00110 |
Grade A, and why
autonomy-tiers 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomy Tiers (T1 / T2 / T3)
Autonomy tiers control where humans checkpoint during BUILD. Every feature gets a tier in SHAPE. The tier shapes the build's pause behavior.
The three tiers
| Tier | Test phase | Build phase | Commit phase |
|---|---|---|---|
| T1 | Auto | Auto | Auto-commit |
| T2 | Auto | Auto | Checkpoint before commit |
| T3 | Checkpoint | Checkpoint | Checkpoint before commit |
Where "checkpoint" means: the agent stops and surfaces what it's about to do; the human approves before it proceeds.
Decision tree
For every feature in SHAPE, ask in order:
- Does this feature touch IDENTITY.md (WHO/JOB/NEVER) or Architecture Constraints? → T3
- Could this feature break a published contract (API/schema/event)? → T3
- Does this feature touch a hot path or modify recently-shipped code? → T2
- Does this feature have unclear intent or weak test coverage in the affected module? → T2
- Otherwise → T1
What T1 looks like in practice
You start /forge:build, the orchestrator dispatches test-writer + builder, the loop runs to green, autonomous commit. You see a --- CONTEXT BOUNDARY -- starting feature: {id} --- line, then later a "feature done, quality_score 9" summary. No interruption.
T1 is for: utility refactors, simple CRUD additions, adding optional fields, internal tooling, debt with clear scope.
What T2 looks like
The build runs autonomously through tests + implementation, but stops before commit. The agent shows you the diff and says: "All tests pass. Approve to commit?" You inspect, then y or fix-then-commit.
T2 is the default for most features. It's the cheapest way to keep humans in the loop without bottlenecking on every change.
What T3 looks like
The build pauses before writing tests and running the build. You're approving the test plan before code exists, then the implementation diff before commit. Two checkpoints per feature.
T3 is for: identity changes (rare), contract-breaking changes, hot-path modifications, security-sensitive code, anything where "looks right" isn't enough.
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 · 82 lines · 102 tokens per session scan A f969c616a620
autonomy-tiers is a skill published in the GitHub repository dormstern/forge (6 stars, last pushed 3mo ago), licensed MIT. It adds 102 tokens to every session and 1,096 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.
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…