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/yknnv/brownspec/standardsnpx skills add yknnv/brownspec --skill standardsgit clone --depth 1 https://github.com/yknnv/brownspecWrote 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/yknnv/brownspec/standards)<a href="https://agentmods.dev/skills/yknnv/brownspec/standards"><img src="https://agentmods.dev/badge/skills/yknnv/brownspec/standards.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 | $0.00065 | $0.00945 |
| Opus 5 | $0.00032 | $0.00473 |
| Sonnet 5 | $0.00013 | $0.00189 |
| Haiku 4.5 | $0.00006 | $0.00094 |
Grade A, and why
standards 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bootstrap .brownspec/
First run in a repository. Produces three things:
| File | Who writes it | On re-run |
|---|---|---|
.brownspec/project-map.json |
generated | overwritten |
.brownspec/conventions.md |
generated, user corrects | overwritten |
.brownspec/policies.md |
people — security, architecture | never touched |
The one rule that cannot be broken
If .brownspec/policies.md exists, do not write to it. Do not reformat it, do not
merge into it, do not append a section, do not "helpfully" fill in a blank. Create it
only when it is absent, and only from
${CLAUDE_PLUGIN_ROOT}/templates/policies.md.tmpl — an unmodified stub.
That file holds requirements a security team signed off on. Overwriting it with inferred content would delete a control and leave a plausible-looking document in its place, and nobody would notice until an audit. Conventions are cheap to regenerate; policies are not.
Before writing anything, check whether it exists. If it does, say so and leave it alone.
Phase 1 — Map
Run level 1 from the repo-reading skill. Write .brownspec/project-map.json.
Phase 2 — Conventions
Run level 2 from the repo-reading skill. Sample two or three modules — prefer the
ones with the most recent activity in git log, since stale modules teach stale
conventions. Fill in ${CLAUDE_PLUGIN_ROOT}/templates/conventions.md.tmpl and write
.brownspec/conventions.md.
Sources, in order of trust: the code itself where it is consistent, then linter and
formatter configuration, CI pipeline definitions, CONTRIBUTING.md, ADRs, PR templates,
and any existing CLAUDE.md. Prefer what the code does over what a document claims.
Where a document and the code disagree, that disagreement is itself worth recording.
Every rule carries a short real excerpt and the path it came from. A rule with no example is an opinion, and the next agent to read this file will not be able to apply it.
Where the codebase contradicts itself, record both variants in the Inconsistencies table rather than picking one. Do not resolve it silently — that is the user's call, and it is usually the most interesting thing you found.
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.
- 3d ago First seen · 83 lines · 65 tokens per session scan A 04ab7547eb5e
standards is a skill published in the GitHub repository yknnv/brownspec (2 stars, last pushed 6d ago), licensed MIT. It adds 65 tokens to every session and 945 once invoked, about $0.0003 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
prospec-verify
Verify Implementation - Run 5+1 dimension audit (tasks, spec compliance, constitution, knowledge-implementation consistency, tests, design consistency) and assign quality grade (S/A/B/C/D). Triggers: verify, audit, quality check, 驗證, 稽核, 品質檢查, 評級.
prospec-archive
Archive Changes - Archive completed changes, generate summary, sync requirements to feature specs, and gate archiving on Knowledge sync. Triggers: archive, spec sync, finalize change, 封存, 歸檔, 收尾, 規格同步.
prospec-knowledge-generate
Generate AI Knowledge - Read raw-scan.md, analyze project structure, autonomously decide module boundaries, and produce Recipe-First module READMEs and index. Triggers: generate knowledge, analyze project, module split, 產生知識, 知識庫, 分析專案, 模組拆分.
release
Cut a prospec GitHub release — bump version strings, tag, and publish release notes in the established format so the Release Binaries workflow attaches multi-platform binaries. Triggers: release, publish release, cut a release, ship a version, 發布, 發佈, 出版本, 發版, 版本發布, 發布 release.
submit-pr
Open a prospec pull request in the house format — push the change's two commits, write the Traditional Chinese body, and link it to its issue. Triggers: submit pr, open pr, 開 PR, 送 PR, 發 PR, pull request, 提交 PR.
submit-issue
Open a prospec GitHub issue in the house format — conventional-commit title, Traditional Chinese body (problem → solutions → acceptance criteria), downstream-compatibility block, series cross-links, and optional model-routing guidance. Triggers: submit issue, open issue, create issue, file issue, 開 issue, 發 issue, 建…