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.
curl -O https://raw.githubusercontent.com/elidickinson/pi-claude-bridge/main/AGENTS.mdgit clone --depth 1 https://github.com/elidickinson/pi-claude-bridgeWrote 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/elidickinson/pi-claude-bridge/agents-md)<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.
<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>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 | $0.00836 | $0.00836 |
| Opus 5 | $0.00418 | $0.00418 |
| Sonnet 5 | $0.00167 | $0.00167 |
| Haiku 4.5 | $0.00084 | $0.00084 |
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 9d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guidelines
Restricted Actions
Do not auto-commit.
Do not interact with the public without explicit permission. For example, do not open PRs or comment on github issues unless I say so.
Claims about how Claude Code behaves
~/.claude/projects/** is not evidence of what CC does. The bridge writes into
the same files and CC re-serializes imported records under synthetic ids, so a scan
of that directory largely reflects our own output handed back to us — 352 of 1,810
files hold both shapes. Before asserting "CC does X" from disk, split by provenance
(CC-live records carry a real requestId/promptId; ours carry
msg_syn_*/req_syn_*) and regroup by message.id, since CC stores one content
block per record while cc-session-io stores one record per message.
diag/audit-transcripts.mjs does both.
Better still, prove it with a live probe. tests/int-cc-contracts.mjs pins each
undocumented behavior we depend on against the installed CC/SDK and is the right
home for a new assumption; diag/capture-proxy.mjs captures the actual request
bodies when the question is what CC sends. claude-code-rip/ lags the installed
CLI by an unknown margin, so read it for mechanism, never for current behavior:
what it gates, defaults, or omits may already have changed. And before
reverse-engineering an SDK option at all, grep
node_modules/@anthropic-ai/claude-agent-sdk/sdk.d.ts — it documents every
settings field, several of which solve problems the CC source makes look
intractable.
The same skepticism applies to any rate computed from the debug log. Before
believing one, check the metric against a case whose answer you know: the
cache-break scanner counted a request's uncached input as if the next request
should read it back, which turned every tool-heavy turn into a false break and
manufactured a dose-response that looked like a real finding.
Bin by era before comparing groups. A correlation computed over a window that straddles the onset of the phenomenon will credit whatever else changed. Three independent analyses agreed one account state was safe on 5,611 clean requests — every one of which predated the first failure; switching to that state reproduced the failure in five minutes.
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.
- 9d ago First seen · 71 lines · 836 tokens per session scan A 997590c30b46
pi-claude-bridge AGENTS.md is an instructions file published in the GitHub repository elidickinson/pi-claude-bridge (365 stars, last pushed today), licensed MIT. It adds 836 tokens to every session, about $0.0042 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 instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.