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 mrclrchtr/supi --skill claude-md-revisiongit clone --depth 1 https://github.com/mrclrchtr/supiWrote 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/mrclrchtr/supi/claude-md-revision)<a href="https://agentmods.dev/skills/mrclrchtr/supi/claude-md-revision"><img src="https://agentmods.dev/badge/skills/mrclrchtr/supi/claude-md-revision/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/skills/mrclrchtr/supi/claude-md-revision"><img src="https://agentmods.dev/badge/skills/mrclrchtr/supi/claude-md-revision.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00045 | $0.01746 |
| Opus 5 | $0.00023 | $0.00873 |
| Sonnet 5 | $0.00009 | $0.00349 |
| Haiku 4.5 | $0.00005 | $0.00175 |
Grade A, and why
claude-md-revision 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Revise CLAUDE.md with Session Learnings
Review the current session for actionable learnings and update the project's CLAUDE.md or .claude.local.md files. The goal is concise, durable context that helps future sessions work more effectively in this codebase.
Workflow
Step 1: Reflect
Identify what context would have helped this session go smoother. Scan the conversation for learnings worth preserving.
What TO capture:
- Non-obvious commands/workflows discovered or used repeatedly (not routine build/test/lint — those are in package.json)
- Gotchas and non-obvious patterns (deprecated APIs, common pitfalls, tricky behaviors)
- Package relationships or ordering dependencies not obvious from code
- Testing approaches that worked (or didn't)
- Configuration quirks (env vars, build tools, path oddities)
What NOT to capture:
- Obvious info already clear from code or naming
- Generic best practices ("write tests", "use meaningful names")
- One-off fixes unlikely to recur ("fixed typo on line 42")
- Routine/easy-to-find commands:
npm install,npm test,npm run build— these are in package.json or README and don't earn their place in the context window - Verbose explanations — one line per concept; link to docs for detail
- Static facts SuPi already provides on the first turn or through routine
code_orientation: package/module tables, manifest dependency graphs, project trees, direct directory inventories, and package manifest declarations
Filter ruthlessly. Every token must earn its place in the instruction file — if content doesn't save future sessions more time than it costs to read, remove it.
Before adding, consider removing. Scan the file for content that MUST be removed or compressed. Never skip removals because of edit churn—a one-time edit that saves tokens on every relevant load pays for itself quickly:
- Routine command listings that are trivially discoverable from
package.json— MUST remove (~50–200 tokens saved per session) - Sections that duplicate the complete first-turn module overview or facts available through routine
code_orientation(package tables/paths, manifest dependency graphs, static project trees, direct directory listings, manifest declarations) — MUST remove unless they add ownership, flow, boundary, exception, or rationale - Verbose explanations where a one-liner suffices — compress (~20–100 tokens saved)
- Stale commands, paths, or architecture descriptions that no longer match the codebase — remove
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 143 lines · 45 tokens per session scan A 880f5ce2bb37
claude-md-revision is a skill published in the GitHub repository mrclrchtr/supi (89 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 1,746 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 2026-08-30.
Other skills, from other repositories
review
Review a change for correctness, security, and missing tests.
gh-address-comments
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
pi-parity-review
Adversarially verify that a ported change is faithful to the original pi implementation (TS source + published npm build). Use after porting upstream pi changes, or standalone on any area of this repo ("is X faithful to pi?").
pi-go-review
Review ported Go code for idiomatic quality — that the port maximizes Go rather than transliterating TypeScript. Use after porting upstream pi changes, or standalone on any diff in this repo.
review-pr
Deeply review a GitHub pull request.
ragcode-memory
Manage shared cross-AI memories for this project through RagCode MCP tools (memorywrite, memoryquery, memorylist, memorydelete), with ragcode memory CLI fallback when MCP is unavailable. Read prior decisions, user preferences, and feedback written by other AI agents, and record new insights so they persist across…