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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/michaelycjo/specseal/claude-md"><img src="https://agentmods.dev/badge/instructions/michaelycjo/specseal/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00818 | $0.00818 |
| Opus 5.5 | $0.00327 | $0.00327 |
| Sonnet 5.5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
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 4d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The goal a design is chosen against
Verification through an automated workflow is this project's first goal. Between two designs that catch the same defect, the one that stops to ask a person is the more expensive, and the difference has to be argued rather than assumed. Time and stability are what the argument is being made for.
This is a goal, not a rule, which is why it sits above them: it decides
between options where no rule is broken either way.
skills/implement/SKILL.md 1. Read the spec before the code holds the rule
this goal produces for a session, with its reasoning: whatever needs a person
is asked once, together, before the first edit, and nothing comes back mid-run.
The rule a mechanism is kept against
A mechanism stays only while its history shows what it caught against what
it costs; existing is no reason to keep it. A gate that stops a session,
the routing check among them, guards the work a work item owns. A change
that would be routed no work item, such as a formatter run, a dependency
bump or an identifier renamed across files by sed, is outside that work, so
where only such a change passes through a gap in that kind of gate, the gap
is not a weakness to close. A rule's proof
is the test or behaviour eval its check: line names. A fact has one source,
and every other place links to it. A check gates only a fact it reads; a
noisy reading, or one guessed from words, is a report. Nothing is kept beside
the tree to stay in step with it, such as a stored count or coordinate. Do
not avoid the change a problem calls for: before a fix adapts to an existing
structure, ask whether the structure should change, and when fixes chase one
mechanism's edge cases, ask what it decides; what exists is a reference, not
a constraint. A thing is re-checked only when the diff or CI shows it
changed. A change rewrites the text it amends in place, and in the same
commit removes what stood on the old fact: a check, an exception, a comment,
a copy. History goes to git, the changelog and the work record.
CONTRIBUTING.md What a change to a gate must carry is where a pull
request answers this rule and the goal above.
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.
- 4d ago Changed · +5 lines · +87 tokens per session 8bc3074839f3
- 7d ago Changed · -35 lines · -1,270 tokens per session cbb4ef4c8cf4
- 14d ago Changed · -8 lines · -171 tokens per session 905443a55f96
- 17d ago Changed · +42 tokens per session 060becb9313c
- 26d ago Changed · -19 lines · -222 tokens per session f9f80c84e1ee
- 27d ago Changed · -93 lines · -1,251 tokens per session f4b1b0375897
- 1mo ago Changed · +4 lines · +86 tokens per session d33515e31a54
- 1mo ago Changed · +18 lines · +309 tokens per session 7b9bf2ea4b25
- 1mo ago Changed · +20 lines · +276 tokens per session ea248f480021
- 1mo ago First seen · 168 lines · 2,932 tokens per session scan A 9b78b4576b79
SpecSeal CLAUDE.md is an instructions file published in the GitHub repository MichaelYcJo/SpecSeal (1 stars, last pushed 4d ago), licensed MIT. It adds 818 tokens to every session, about $0.0033 per session on Opus 5.5. 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
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.