What is pi-claude-bridge AGENTS.md?

A project instruction file for the Claude Code bridge, describing agent rules, restricted actions, and how to verify claims about Claude Code’s behaviour.

Use it when changing or investigating the bridge, especially when checking Claude Code’s file formats, requests, or undocumented behaviour.

It helps prevent unsupported conclusions and actions such as automatic commits or public GitHub activity. It also points contributors to tests and request captures when documentation or stored files are misleading.

How elidickinson/pi-claude-bridge configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to elidickinson/pi-claude-bridge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/elidickinson/pi-claude-bridge/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/elidickinson/pi-claude-bridge

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/elidickinson/pi-claude-bridge/agents-md/github.svg)](https://agentmods.dev/instructions/elidickinson/pi-claude-bridge/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/elidickinson/pi-claude-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/elidickinson/pi-claude-bridge/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/elidickinson/pi-claude-bridge/agents-md"><img src="https://agentmods.dev/badge/instructions/elidickinson/pi-claude-bridge/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 676 This file is loaded in full into every session.

When invoked 676 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00676	$0.00676
Opus 5.5	$0.00270	$0.00270
Sonnet 5.5	$0.00135	$0.00135
Haiku 4.5	$0.00068	$0.00068

Measured yesterday against content hash a141a35f2f33, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pi-claude-bridge AGENTS.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 yesterday.

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.

AGENTS.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guidelines

Claims about how Claude Code behaves

~/.claude/projects/** is not evidence of what CC does -- the bridge writes there too, and CC re-serializes imported records under synthetic ids. Split by provenance (CC-live: real requestId/promptId; ours: msg_syn_*/req_syn_*) and regroup by message.id (diag/audit-transcripts.mjs does both).

Better: prove it with a live probe. tests/int-cc-contracts.mjs pins undocumented behavior against the installed CC/SDK; diag/capture-proxy.mjs captures request bodies. claude-code-rip/ is mechanism only, never current behavior. Before reverse-engineering an SDK option, grep node_modules/@anthropic-ai/claude-agent-sdk/sdk.d.ts first.

Validate any rate from the debug log on a case whose answer you know. Bin by era before comparing groups -- a window straddling the onset credits whatever else changed.

Five wrong conclusions across two sessions came from skipping the above.

Changelog

Maintain an entry in the ## UNRELEASED section at the top of CHANGELOG.md for every significant change, using the existing format:

- **Tag: summary** — detail

Do not add changelog entries for docs-only changes, or for small changes (especially test-only ones) unless they relate to an issue. Combine multiple UNRELEASED entries about the same feature into one. Test, debug and docs entries generally go last.

Keep entries short: one sentence of detail is usually enough. Only a big change warrants a few sentences. Leave implementation details and file lists to the commit log and docs.

Tags: Add, Fix, Refactor, Tests, Bump, Deprecate, Remove, Debug, Breaking.

Release

No build step — the package ships src TypeScript as-is (see files in package.json). To cut version X.Y.Z:

Changelog — rename the ## UNRELEASED section to ## X.Y.Z — YYYY-MM-DD.
Bump — set version to X.Y.Z in package.json.
Commit — git commit -m "Release X.Y.Z" (changelog + package.json only).
Tag — git tag -a vX.Y.Z -m "X.Y.Z" (note the v prefix; annotated so --follow-tags pushes it).
Push commit and tag together — git push --follow-tags.
Publish — npm login and npm publish.

Read the full file on GitHub · 45 lines

Changes

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.

yesterday Changed · +2 lines · +69 tokens per session a141a35f2f33
2d ago Changed · +3 tokens per session c1ca48e67dff
7d ago Changed · +4 lines · +84 tokens per session 8a8c002f9947
1mo ago Changed · -32 lines · -316 tokens per session fb19f84124ce
2mo ago First seen · 71 lines · 836 tokens per session scan A 997590c30b46

Subscribe to this mod's changes

pi-claude-bridge AGENTS.md is an instructions file published in the GitHub repository elidickinson/pi-claude-bridge (775 stars, last pushed yesterday), licensed MIT. It adds 676 tokens to every session, about $0.0027 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.

pi-claude-bridge AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pi-claude-bridge AGENTS.mdelidickinson/pi-claude-bridge	Instructions file	775	yesterday	MIT	A	676	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

pi-claude-bridge: Instructions file for Codex