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/johnny-z13/proofslip/claude-mdgit clone --depth 1 https://github.com/Johnny-Z13/proofslipWrote 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/johnny-z13/proofslip/claude-md)<a href="https://agentmods.dev/instructions/johnny-z13/proofslip/claude-md"><img src="https://agentmods.dev/badge/instructions/johnny-z13/proofslip/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 | $0.01608 | $0.01608 |
| Opus 5 | $0.00804 | $0.00804 |
| Sonnet 5 | $0.00322 | $0.00322 |
| Haiku 4.5 | $0.00161 | $0.00161 |
Grade A, and why
proofslip 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 5d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ProofSlip
Portable proof objects for agent workflows.
Live
- Production: https://proofslip.ai
- Domain: proofslip.ai
- Sister product: ContextCapsule — same ecosystem, shared design language
- ContextCapsule repo: ~/Projects/Products/context-capsule (keep READMEs and CLAUDE.md cross-referenced)
Product Position
ProofSlip and ContextCapsule are two primitives for reliable agent workflows:
- ProofSlip (evidential) — "Here's what actually happened, and you can verify it."
- ContextCapsule (navigational) — "Here's the situation, what matters, and what should happen next."
ProofSlip creates verifiable receipts that prove actions happened. Agents check receipts before deciding what to do next. Receipts are ephemeral (24h default), typed, and include polling guidance for non-terminal states.
Published Packages
- MCP Server:
@proofslip/mcp-serveron npm — also registered on official MCP registry asai.proofslip/mcp-server - LangChain Tools:
langchain-proofslipon PyPI — 3 tools + toolkit for Python agent frameworks - Listings: Smithery (mcp.so), Glama.ai, official MCP registry, PulseMCP (auto-ingests)
Tech Stack
- Runtime: Node.js 18+
- Framework: Hono v4
- ORM: Drizzle ORM with Neon PostgreSQL
- Language: TypeScript (strict mode)
- Deployment: Vercel serverless
- Testing: Vitest
- MCP: @modelcontextprotocol/sdk for MCP server package
- Python packages: Built with setuptools, published via twine
Development
npm run dev # Local dev server
npm test # Run tests (watch mode)
npm run test:all # Full stack test — 4 layers, ~184 tests, summary report
npm run test:unit # Unit + integration only
npm run test:smoke # Smoke tests against production (needs PROOFSLIP_API_KEY in .env)
npm run test:packages # MCP server package tests
npm run db:generate # Generate migrations
npm run db:migrate # Apply migrations
npm run db:seed # Seed API key (npm run db:seed -- [email protected])
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.
- 5d ago First seen · 138 lines · 1,608 tokens per session scan A 7f0a43ab3bbf
proofslip CLAUDE.md is an instructions file published in the GitHub repository Johnny-Z13/proofslip (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,608 tokens to every session, about $0.0080 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
do-it AGENTS.md
AGENTS.md instructions for tdwhere123/do-it, covering agents.md, file rules, repository, source of truth vs build artifacts and closed-set contracts.
opendigitalproductfactory AGENTS.md
AGENTS.md instructions for OpenDigitalProductFactory/opendigitalproductfactory, covering dpf — agent rulebook, 1. first principles, 2. project architecture, 3. branching, commits & prs and 4. verification — build gate (mandatory).
codex-acp-bridge AGENTS.md
AGENTS.md instructions for normahq/codex-acp-bridge, covering codex-acp-bridge — agents.md, development standards, quality gates (required), logging policy and bridge guardrails.
opendigitalproductfactory copilot-instructions.md
Copilot instructions for OpenDigitalProductFactory/opendigitalproductfactory: Read /AGENTS.md at the repo root before any work in this project. It is the canonical rulebook; tool-specific files in this repo are pointers to it.
pi CLAUDE.md
Instructions for share-skills/pi, covering 强制, 内部目标（不可写入公开文件）, 跑分规范 and eval 驱动优化规则.
codebadger AGENTS.md
AGENTS.md instructions for qcri/codebadger, covering codebadger agent guide, what this repository is, development workflow, cpg and worker rules and mcp/tool contracts.