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 instructions/sgroy10/speclock/agents-mdgit clone --depth 1 https://github.com/sgroy10/speclockWhat 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 | $0.00262 | $0.00262 |
| Opus 5 | $0.00131 | $0.00131 |
| Sonnet 5 | $0.00052 | $0.00052 |
| Haiku 4.5 | $0.00026 | $0.00026 |
Grade A, and why
speclock AGENTS.md 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.
What it actually says
SpecLock Development Guide
Project
SpecLock is an MIT-licensed Node.js AI constraint engine. Keep changes focused, preserve the public CLI and MCP APIs, and do not weaken enforcement behavior.
Required checks
- Run
npx speclock check "<planned action>"before changing code. - Run
npm testbefore proposing a release. - Changes under
src/require a version bump in every location documented inCLAUDE.md. Documentation, metadata, tests, and plugin packaging do not. - Never publish, deploy, tag, push, or create a pull request without explicit maintainer approval.
Security
- Do not commit credentials, deployment identifiers, customer data, or rules copied from another project.
- Claude Code hook handlers must parse JSON from stdin, cap untrusted input sizes, and fail open on internal errors.
- Hard enforcement may deny an action only when SpecLock itself reports a blocked conflict. Advisory conflicts must remain warnings.
Compatibility
- Node.js 18 and later are supported.
- Keep the local stdio MCP server compatible with Claude Code, Cursor, Windsurf, Cline, Codex, and other MCP clients.
- Use current official Claude Code plugin and hook schemas.
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 · 32 lines · 262 tokens per session scan A 70d32b65ef3d
speclock AGENTS.md is an instructions file published in the GitHub repository sgroy10/speclock (25 stars, last pushed 15d ago), licensed MIT. It adds 262 tokens to every session, about $0.0013 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 instructions, from other repositories
superpowers-zh CLAUDE.md
Instructions for jnMetaCode/superpowers-zh, covering superpowers — 贡献者指南, 如果你是 ai agent, pull request 要求, 我们不会接受的内容 and 第三方依赖.
superpowers-zh GEMINI.md
Instructions for jnMetaCode/superpowers-zh, covering superpowers-zh 中文增强版, 核心规则, 可用 skills and 如何使用.
spec-kit-zh AGENTS.md
Instructions for loulanyue/spec-kit-zh, covering agents.md, about spec kit and specify, general practices, adding new agent support and current supported agents.
Meta_Kim CLAUDE.md
Instructions for KimYx0207/Meta_Kim, covering metakim for claude code, fast read, what this repository is, claude code's role and canonical vs runtime files.
nopua AGENTS.md
Instructions for wuji-labs/nopua, covering nopua · codex 入仓规则, 一 · 项目定位, 二 · 起手必读, 三 · 工程与研究纪律 and 四 · 对外署名.
claude-code-blueprint CLAUDE.md
Instructions for faizkhairi/claude-code-blueprint, covering global claude behavior rules, verify-after-complete (mandatory), what to verify depends on what was built, verification mindset and after verification.