Borrowing it
Nothing to install: this file belongs to MichaelYcJo/SpecSeal. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MichaelYcJo/SpecSeal/main/CLAUDE.mdgit clone --depth 1 https://github.com/MichaelYcJo/SpecSealWrote 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/instructions/michaelycjo/specseal/claude-md)<a href="https://agentmods.dev/instructions/michaelycjo/specseal/claude-md"><img src="https://agentmods.dev/badge/instructions/michaelycjo/specseal/claude-md.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 | $0.02320 | $0.02320 |
| Opus 5 | $0.01160 | $0.01160 |
| Sonnet 5 | $0.00464 | $0.00464 |
| Haiku 4.5 | $0.00232 | $0.00232 |
Grade A, and why
SpecSeal CLAUDE.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 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tooling
- Python: prefer uv · Node.js: prefer pnpm (always respect the project's existing manager).
Safety
- 3+ Fix Rule — same bug, 3 failed fix attempts → STOP. Re-examine the architecture, then ask.
- Verification Gate — no "done / fixed / passes" claim without running the check that proves it and reading its full output.
- Verification Scope — narrow and often, broad once. A slice runs what you just wrote; the handoff to review runs nothing broad; the full suite, lint, and typecheck run once, after the rounds settle. A broad run with an edit after it was spent, not banked.
Session cost
- Batch independent reads and runs — every coordinate a task names in one call, every case from one file in one command. Round-trips are most of a round; cut the trips, never the investigation.
Git
- Run lint/format/typecheck before committing.
- Worktrees only for concurrent sessions on the same tree — single-session work uses
git switch(worktree-guard hook enforces this). - Routing, decided at the start — before the first edit, write
seal/specs/<work-item-id>/routing.mdfromtemplates/sdd-routing.mdand commit it — the write in a command of its own, never batched with the commit. The gate reads that file from the working tree, so a declaration on disk silences the very commit that adds it and no first-commit waiver is needed; but the gate is aPreToolUsehook that denies the WHOLE Bash call, sowrite && git add && git commitin one call writes nothing and the declaration the gate then reports missing is the file that was lost. This is the one place the batching rule above misleads. Ask all three axes as onemultiSelectquestion with three checkboxes, never one at a time: implementation (smith·the session— an optional row), review (through the review chain·straight to the PR) and destination (open the pull request·stop before the pull request). What is checked is the answer, and each box is a row of that file — asking the reviewer in the middle and the pull request at the end is three waits for one decision. The commit gate reads that file, so a declared work item commits silently for either review answer, and CI reads the same file at the pull request. For a change belonging to no work item,[no-review]still waives one command ([no-parity]too where a migration config is declared) — in front of the command, quotes included,: '[no-review]'; git commit …, because aftergit commita bare word is a pathspec and git rejects it. Deciding at the commit is what stops a release mid-run.
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 · +77 lines · +1,161 tokens per session d141a65d0125
- 6d ago First seen · 74 lines · 1,159 tokens per session scan A 4461ccbb015b
SpecSeal CLAUDE.md is an instructions file published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed today), licensed MIT. It adds 2,320 tokens to every session, about $0.0116 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 instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.