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/codervisor/leanspec/leanspec-dev-processnpx skills add codervisor/leanspec --skill leanspec-dev-processgit clone --depth 1 https://github.com/codervisor/leanspecWhat 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 | $0.00160 | $0.02983 |
| Opus 5 | $0.00080 | $0.01491 |
| Sonnet 5 | $0.00032 | $0.00597 |
| Haiku 4.5 | $0.00016 | $0.00298 |
Grade A, and why
leanspec-dev-process 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 2d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
leanspec-dev-process
The spec-issue-driven development (SDD) loop on lean-spec. Every non-trivial change starts as a GitHub spec issue on codervisor/leanspec, proceeds through a PR that references it, and closes when the PR merges.
Lean-spec is its own dogfood: we use the SDD loop we ship. The historical specs/ directory is frozen as a snapshot of pre-migration work; new specs are GitHub issues. This is the same shape as Onsager's and Duhem's loops — the area taxonomy and toolchain checks are lean-spec-specific.
The loop
┌─────────────────────────────────────────────────────────────────┐
│ │
│ idea/request │
│ ↓ │
│ spec(<area>): ... ← issue-spec skill │
│ │ │
│ ↓ │
│ branch + implement │
│ │ │
│ ↓ │
│ leanspec-pre-push ← merge preview, typecheck, test, clippy │
│ │ │
│ ↓ │
│ git push → open PR (body: "Closes #N" or "Part of #N") │
│ │ │
│ ↓ │
│ leanspec-pr-lifecycle ← CI triage, review, iterate │
│ │ │
│ ↓ │
│ merge │
│ │ │
│ │ Closes #N → GitHub auto-closes spec │
│ │ Part of #N → tick Plan items manually (pr-lifecycle) │
│ ↓ │
│ spec closed (Closes) OR Plan items ticked (Part of) │
│ │
└─────────────────────────────────────────────────────────────────┘
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.
- 2d ago First seen · 179 lines · 160 tokens per session scan A 26c2e6dd5b2a
leanspec-dev-process is a skill published in the GitHub repository codervisor/leanspec (287 stars, last pushed 3mo ago), licensed MIT. It adds 160 tokens to every session and 2,983 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.
Other skills, from other repositories
add-community-extension
Add a community extension to the Spec Kit catalog from a GitHub issue submission. USE FOR: processing extension submission issues, validating catalog entries, updating catalog.community.json and docs/community/extensions.md, creating PRs. DO NOT USE FOR: creating new extensions from scratch, or first-party extension…
specrate
Skill to manage specs and changes. Use this when working with specrate-managed documents.
openspec-verify-change
Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
comet-native
Comet Native 工作流。当用户明确调用 /comet-native、要求启动或恢复 Native change，或入口路由到 Native 时使用。.
comet-design
Comet Classic 阶段 2 —— 为 change 产出深度技术 Design Doc。.