Borrowing it
Nothing to install: this file belongs to ashaychangwani/imprint. 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/ashaychangwani/imprint/main/CLAUDE.mdgit clone --depth 1 https://github.com/ashaychangwani/imprintWrote 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/ashaychangwani/imprint/claude-md)<a href="https://agentmods.dev/instructions/ashaychangwani/imprint/claude-md"><img src="https://agentmods.dev/badge/instructions/ashaychangwani/imprint/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/ashaychangwani/imprint/claude-md"><img src="https://agentmods.dev/badge/instructions/ashaychangwani/imprint/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 | $0.02882 | $0.02882 |
| Opus 5.5 | $0.01153 | $0.01153 |
| Sonnet 5.5 | $0.00576 | $0.00576 |
| Haiku 4.5 | $0.00288 | $0.00288 |
Grade A, and why
imprint 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 15d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Imprint — agent context
Imprint is a CLI tool: record a real browser session once, get back two deterministic replay artifacts (an API workflow + a DOM playbook) plus a generated MCP tool an AI agent can call. "Postman for AI agents."
Status
v0.1 shipped. Star demos: examples/google-flights (4 tools, audit 92.6%) and examples/google-hotels (4 tools, audit 91.7%) — each one-shot compiled from a single real browser-session recording via imprint teach, decoding Google's batchexecute nested-array wire format with producer→consumer token chaining (search → booking/reviews). Other working demos: examples/southwest (live, defeats Akamai via stealth-fetch) and examples/discoverandgo (authed museum-pass booking). examples/echo is the MCP smoke-test fixture. Deferred work lives in TODOS.md.
Where to look
- Architecture + module map: docs/architecture.md
- Glossary (Workflow, Playbook, Backend, Stealth-fetch, etc.): docs/glossary.md
- Decisions log (why YAML, why ladder, why MCP-stdio default): docs/decisions.md
- Getting started (60-second quickstart): docs/getting-started.md
- Troubleshooting: docs/troubleshooting.md
- Original design doc (April 2026 office-hours approval): docs/design.md
- Capture protocol (CDP details): docs/capture-protocol.md
- Playbook debugging: docs/playbook-debugging.md
- Notification setup: docs/notifications.md
- Security model + redaction guarantees: docs/security.md
- Website: web/ — standalone Vite/React landing page deployed with Vercel using
webas project root
Project layout
src/
├── cli.ts # 19 verbs (run `imprint --help`)
├── imprint/ # core modules — see docs/architecture.md for the map
examples/
├── <site>/<toolName>/{workflow.json, playbook.yaml, index.ts, cron.json, backends.json}
prompts/
├── compile-agent.md # generate (workflow.json/parser.ts) system prompt
├── request-triage.md # compile-playbook request filtering prompt
├── playbook-compilation.md # compile-playbook (playbook.yaml) system prompt
docs/ # human-facing documentation
web/ # standalone Vite/React landing page; run web commands from web/
test/ # bun test, ~977 tests across ~56 files
scripts/ # smoke tests + one-off dev helpers
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.
- 15d ago Changed · +50 lines · +394 tokens per session ffafe6e1a4e0
- 2mo ago First seen · 137 lines · 2,488 tokens per session scan A 86ec0a35cc0d
imprint CLAUDE.md is an instructions file published in the GitHub repository ashaychangwani/imprint (24 stars, last pushed 15d ago), licensed MIT. It adds 2,882 tokens to every session, about $0.0115 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 2026-08-30.
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.