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/bks-lab/open-bridge/claude-mdgit clone --depth 1 https://github.com/bks-lab/open-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/bks-lab/open-bridge/claude-md)<a href="https://agentmods.dev/instructions/bks-lab/open-bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/bks-lab/open-bridge/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 | $0.00551 | $0.00551 |
| Opus 5 | $0.00275 | $0.00275 |
| Sonnet 5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
open-bridge 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.
What it actually says
@AGENTS.md
Claude Code specifics
The canonical, tool-agnostic operating manual for this repo is the ~800-line
AGENTS.md
(Linux-Foundation convention, read natively by Codex/Cursor/Copilot/Gemini). It is inlined
above via @AGENTS.md, so the full manual — session-start gate, rules, task management, agents,
standing orders, commands — is already in your context. This file only adds the
Claude-Code-specific bits.
The project registry (ecosystem.yaml, created at onboarding, gitignored) is no longer
@-imported. It is indexed: Phase 1 runs
python3 scripts/context-index.py ecosystem.yaml, which emits the settings verbatim and one
line per repo, customer and workspace; the entry itself arrives with --get <name> when
somebody names one. The registry is the always-on file that grows with the instance rather
than with this repo, and reading it whole meant carrying a paragraph about every project in
order to know that the project exists. Details: docs/context-index.md.
That trade has a real cost worth naming: an @-import is resident for the whole session,
while a Phase 1 read is ordinary conversation and can be compacted away later. The card is
small enough to re-run, and --get is always available; a file large enough to matter here is
too large to keep resident on that argument alone.
Onboarding appends further @-imports here as it seeds the live USER files
(e.g. identity/agent/SOUL.md + IDENTITY.md).
Run the Phase-0 session-start gate before responding. Belt-and-suspenders, so the gate
survives even if the import above fails to resolve:
Do not answer the first user message (even "hi", "status", "what can you do") before running Phase 0.
Phase 0 mechanic, inlined here so it works even if @AGENTS.md is silently dropped: detect the
current branch + whether a user/* branch exists + whether bridge-config.yaml is present, and
route accordingly — on the core branch with no user/* and no bridge-config.yaml, trigger the
NEW USER path (/bridge-onboard); otherwise route to the matching state (wrong-branch, orphan,
broken-config, or normal task-management load).
If @AGENTS.md does not resolve in your harness, read AGENTS.md manually before responding.
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 · 38 lines · 551 tokens per session scan A 0a4e6e47be7d
open-bridge CLAUDE.md is an instructions file published in the GitHub repository bks-lab/open-bridge (8 stars, last pushed 5d ago), licensed MIT. It adds 551 tokens to every session, about $0.0028 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
swarm-357 CLAUDE.md
Instructions for TechTideOhio/swarm-357, covering claude.md, what this repo is, python package (packages/techtide-swarm/), or from pypi and key classes.
theboringoffice CLAUDE.md
Instructions for theboringhumane/theboringoffice: This project is served by theboringoffice: the oikonomos manager protocol imported below is the operating charter. @.opencode/oikonomos.md.
Meterless AGENTS.md
Instructions for Meterless/Meterless, covering agent instructions for meterless, routing table, isolation rule, repo-wide rules and non-coding agents.
Agent-Context CLAUDE.md
Claude Code instructions for lx-wnk/Agent-Context, covering claude.md, project overview, commands, format all files and check formatting (ci-style).
agent-skills AGENTS.md
AGENTS.md instructions for simota/agent-skills, covering agents.md — claude-skills, repository purpose, language policy, repository structure and skill authoring conventions.
babysitter CLAUDE.md
Claude Code instructions for a5c-ai/babysitter, covering claude.md, repo-specific overrides, read these first, quick commands and claude code local notes.