Borrowing it
Nothing to install: this file belongs to IgnacioMarin402/spec-flow-plugin. 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/IgnacioMarin402/spec-flow-plugin/main/CLAUDE.mdgit clone --depth 1 https://github.com/IgnacioMarin402/spec-flow-pluginWrote 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/ignaciomarin402/spec-flow-plugin/claude-md)<a href="https://agentmods.dev/instructions/ignaciomarin402/spec-flow-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/ignaciomarin402/spec-flow-plugin/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/ignaciomarin402/spec-flow-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/ignaciomarin402/spec-flow-plugin/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 | $0.00572 | $0.00572 |
| Opus 5.5 | $0.00229 | $0.00229 |
| Sonnet 5.5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
spec-flow-plugin 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 11d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working agreements for this repo
This engine closes one failure: a check that looks armed and is not. Work on the engine is held to the same bar.
Evidence
- A claim needs a run behind it. Reading code forms a hypothesis; running it tests one.
- Every fix gets a regression test, run against the commit before the fix,
in a throwaway clone (
git clone . <tmp> && git checkout <sha>) — never by stashing or checking out in this tree. Say which tests prove the defect (fail before) and which only guard new behaviour (pass both ways). - Before removing something, list every job it does and who else does each. Before enforcing something, check what its siblings get.
Coupled contracts
The hooks share .claude/state/phase; the agents share the shape of Mk.md;
the commands describe both. After changing one member, re-read every file that
reads or writes the same thing — each still reads correctly on its own, which
is why the break is silent.
Merging
- A branch is tested on the
mainit merges into. Bringmainin before opening the PR, and again whenevermainmoves. Two PRs can each pass on their own and break each other with no textual conflict. - Merge only on green CI. With plugin auto-update on, a change on
mainreaches every session that runs the engine.
Where reasoning goes
- Invariant (why this line must be so) → a short comment beside it.
- Transition (what it used to be, and why it changed) → the commit body.
Recover one with
git log -S '<code>' -- <file>,git log -L <a>,<b>:<file>orgit blame -L <n>,<n> <file>. - Decision (why the system has this shape, and what was refused) →
decisions/, cited from the code asADR-NNN.
Details: .claude/skills/engine-comments.
Docs
Less is the goal. Delete prose that restates the code, the git history or a check. Prefer a check over a sentence — counts written as prose drift.
New prose files or directories go in SCAN_FILES / SCAN_DIRS in
scripts/no-repo-refs.mjs, and in the written-out list in
scripts/coupling-fixture.mjs. scripts/plugin-paths.mjs checks that every
${CLAUDE_PLUGIN_ROOT}/... path an instruction names actually ships.
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.
- 11d ago Changed · +8 lines · +90 tokens per session 78f68d91ad8b
- 25d ago Changed · -104 lines · -1,322 tokens per session 43bc03a2e7ba
- 1mo ago Changed d140ceb63bf9
- 1mo ago First seen · 148 lines · 1,804 tokens per session scan A 3a99ab791889
spec-flow-plugin CLAUDE.md is an instructions file published in the GitHub repository IgnacioMarin402/spec-flow-plugin (2 stars, last pushed 4d ago), licensed MIT. It adds 572 tokens to every session, about $0.0023 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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.