Borrowing it
Nothing to install: this file belongs to Judgment-Pack/judgment-pack-runtime. 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/Judgment-Pack/judgment-pack-runtime/main/CLAUDE.mdgit clone --depth 1 https://github.com/Judgment-Pack/judgment-pack-runtimeWrote 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/judgment-pack/judgment-pack-runtime/claude-md)<a href="https://agentmods.dev/instructions/judgment-pack/judgment-pack-runtime/claude-md"><img src="https://agentmods.dev/badge/instructions/judgment-pack/judgment-pack-runtime/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/judgment-pack/judgment-pack-runtime/claude-md"><img src="https://agentmods.dev/badge/instructions/judgment-pack/judgment-pack-runtime/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 | $0.01426 | $0.01426 |
| Opus 5.5 | $0.00570 | $0.00570 |
| Sonnet 5.5 | $0.00285 | $0.00285 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
judgment-pack-runtime 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 3d 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.
This is a copy
100% identical to judgment-pack-runtime AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in this repository
This file is read by Codex as AGENTS.md and by Claude as CLAUDE.md; the two are the same text.
Edit AGENTS.md and run scripts/sync-agent-docs.sh to regenerate CLAUDE.md.
Before you open a pull request
- Run
scripts/dev/check.sh(orjpdev checkwhere the kit is installed) once. It runs the checks listed indev.jsonin order and prints one summary block. - Paste that summary block in the pull request body, under a "Checks" heading.
- If a check fails: read its first lines in the block, fix the cause, re-run that one check with
--only NAME, then run the whole list once more. Do not loop on the whole list. - Start no CI watch. Push, report once, and stop; CI owns everything deterministic.
- Push with
jpdev push [BRANCH], or where the kit is not installed withgit -c credential.helper= -c 'credential.helper=!gh auth git-credential' push -u origin BRANCH. The machine's stored git credential can be another account's, and a plaingit pushis then refused; the helper form uses theghlogin. Never store a credential, never change global git configuration, never push with force (jpdev pushrefuses--forceand-f).
Before you hand over
Run these self-checks on the builder's own head before writing the commit message:
- (a) The boundary paths in
dev.json(handover.boundary_paths) show no admission or verdict change unless the issue names one:git diff origin/main...HEAD -- <paths>contains additions to offer tables or new paths only. - (b) Every schema member and enum value the change adds is carried by at least one vector: remove it from a scratch copy of the schema and a vector fails.
- (c) Where two languages read the same vectors, both readers pass over everything added.
- (d) Every mutation row added is caught, and its twin in the other language is caught by hand.
- (e) Every refusal path added emits an event that validates with a malformed input: empty, missing or oversized.
- (f) An interrupted and resumed run carries every new checkpoint member.
- (g) The design's words and the code agree sentence by sentence.
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.
- 3d ago Changed · +9 lines · +234 tokens per session ecdfdcd80238
- 8d ago Changed · +30 lines · +484 tokens per session 1bde766a8219
- 9d ago First seen · 49 lines · 708 tokens per session scan A 6fba63089bbd
judgment-pack-runtime CLAUDE.md is an instructions file published in the GitHub repository Judgment-Pack/judgment-pack-runtime (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,426 tokens to every session, about $0.0057 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to judgment-pack-runtime AGENTS.md, differing in 0 lines, and is treated as a copy.
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.