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 skills add unknowbug/anchorlaw --skill anchor.maintaingit clone --depth 1 https://github.com/unknowbug/anchorlawWrote 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/unknowbug/anchorlaw/anchor.maintain)<a href="https://agentmods.dev/skills/unknowbug/anchorlaw/anchor.maintain"><img src="https://agentmods.dev/badge/skills/unknowbug/anchorlaw/anchor.maintain.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 5.1 | $0.00042 | $0.00585 |
| Opus 5 | $0.00021 | $0.00293 |
| Sonnet 5 | $0.00008 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
anchor.maintain 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- anchor-maintain — 94% identical, 3 lines differ
What it actually says
anchor.maintain — 协议维护工作流
Protocol: spec/protocol-v0.20.md §0 (Universal Quantifier Discipline), §8 (Maturity), §10 (Versioning), §11 (Audit) Layer: L4 (Maintain) — 仅限 Anchorlaw 仓库内部（§14.6：MAY 限于协议自身仓库） Execution: inline
触发场景
在本仓库（Anchorlaw）内修改协议或实现时。外部使用者不需要本 skill。
铁律
- 测试全绿：任何改动必须
python -m pytest --rootdir=python python/tests -q全绿（新增时保持全绿；命令行被沙箱拦截时用包装脚本调pytest.main()）。 - 自指铁律：scanner 必须能扫自己的代码不崩溃（第一律反身应用）。
- 新功能必须配测试：协议宣称的每条行为都要有测试证据，否则 §8 Maturity 标 Unverified。
- 协议文档纪律：
- RFC 2119 措辞（MUST/SHOULD/MAY）分级
- 每个全称声称（any/all/every/never）必须带验证证据或限定实现范围，改协议同步更新 §11 审计表
- v0.x 升版记录真实触发原因，不许无理由升版
- Maturity 表 Latest Evidence 写实测数据，不写「应该可以」
- 通用协议铁律：Anchorlaw 是语言无关协议，禁止过度 Python 化——anchor 抽象 = 声明位置 + 验证载体（§13）；跨语言新特性先在协议定义语言无关语义，再逐语言实现。
- 提交纪律：author 固定
unknowbug（禁止改 user.name）；commit message 英文、动词开头（feat(v0.7): ...）；commit 前测试全绿 + changelog/maturity 同步；push 后 GitHub→GitCode 自动同步。
输出
测试全绿 + 协议文档证据同步 + 规范 commit。
约束
- 测试是协议自身的第一律应用，无测试不改协议。
- C++/TS 的 anchor 实现变化需同步 §13 三语言等价表。
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 Changed 280dca35e08b
- 7d ago First seen · 37 lines · 42 tokens per session scan A edadea8ea01b
anchor.maintain is a skill published in the GitHub repository unknowbug/anchorlaw (5 stars, last pushed 7d ago), licensed MIT. It adds 42 tokens to every session and 585 once invoked, about $0.0002 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
changelog-generator
Generate changelogs from git commits. Use when user says "generate changelog", "update changelog", "what changed since last release", or before preparing a new release.
git-commit
Generate conventional commit messages for Java projects. Use when user says "commit", "create commit", "commit changes", or after completing code changes that need to be committed.
truecourse-hooks
Install, configure, or remove the TrueCourse pre-commit hook.
ring:committing-changes
Commit changes with scope allowlist enforcement, atomic grouping, GPG-signed conventional commits, and trailer management. Detects the repo's PR-validation scope policy before proposing any message. Use when the user asks to commit or has changes ready to record. Skip when the working tree is clean or the user wants…
ring:opening-pull-requests
Open a GitHub Pull Request with automatic base branch detection, scope allowlist enforcement, PR template filling, and post-create base verification. Replaces ring:generating-pr-descriptions. Use after pushing a branch when ready to open a PR. Skip if the branch is not yet pushed or there are uncommitted changes …
ring:shipping-changes
End-to-end git orchestrator: branch → commit → push → PR, with a full plan presented before any execution. Detects base branch and scope allowlist once and propagates to all phases. Use when ready to ship a complete unit of work. Skip if only one phase is needed: commit-only → ring:committing-changes, PR-only →…