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/yongthyuan/agent-context-bridge/agents-mdgit clone --depth 1 https://github.com/Yongthyuan/agent-context-bridgeWhat 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 | $0.00649 | $0.00649 |
| Opus 5 | $0.00324 | $0.00324 |
| Sonnet 5 | $0.00130 | $0.00130 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
agent-context-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 2d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This is a TypeScript ESM project for a local-first agent context bridge. Source code lives in src/, organized by responsibility:
src/adapters/,src/agents/, andsrc/renderers/handle agent integrations and output formats.src/protocol/,src/policy/,src/registry/,src/team/,src/remote/, andsrc/collab/contain coordination features.src/ui/assets/contains the small browser UI.tests/unit/contains focused module tests,tests/scenario/contains CLI/MCP scenarios, andtests/fixtures/stores sample agent transcripts..agent-bridge/is project-local runtime state and should not be committed.
Build, Test, and Development Commands
Requires Node.js >=24. In this WSL workspace, prefer the local conda environment:
node --test tests/**/*.test.ts
node node_modules/typescript/bin/tsc --noEmit
Common npm scripts:
npm test: run all Node test files.npm run test:unit: runtests/unit/*.test.ts.npm run test:scenario: run scenario tests.npm run typecheck: run TypeScript without emitting files.npm run dev -- <command>: run the CLI throughtsx, for examplenpm run dev -- agents list.npm run mcp:dev: run the MCP server throughtsx.
Coding Style & Naming Conventions
Use strict TypeScript with ESM imports and explicit .ts extensions for local modules. Follow the existing style: two-space indentation, double quotes, named exports, camelCase functions/variables, PascalCase types, and descriptive file names such as eventRepository.ts or remoteSync.test.ts. Keep modules small and responsibility-focused; prefer existing service helpers over duplicating CLI logic.
Testing Guidelines
Tests use Node's built-in node:test plus node:assert/strict. Name tests *.test.ts and place them under tests/unit/ or tests/scenario/. Add fixture updates under tests/fixtures/ only when parser behavior requires it. For changes touching CLI, MCP, protocol, policy, sync, or storage behavior, run both the relevant targeted test and npm run typecheck.
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.
- 2d ago First seen · 46 lines · 649 tokens per session scan A 3046ffd7df3a
agent-context-bridge AGENTS.md is an instructions file published in the GitHub repository Yongthyuan/agent-context-bridge (3 stars, last pushed 1mo ago), licensed MIT. It adds 649 tokens to every session, about $0.0032 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
waybill AGENTS.md
Instructions for wardmos/waybill, covering agents.md, privacy, checks, commit messages and git history.
waybill CLAUDE.md
Instructions for wardmos/waybill, a project described as: Continue unfinished coding tasks across agent CLIs with portable handoff bundles.
helmor AGENTS.md
Instructions for dohooo/helmor, covering agents.md, what is helmor, commands, architecture and three-process model.
matt-skills-with-to-goal CLAUDE.md
Instructions for tt-a1i/matt-skills-with-to-goal: Skills are organized into bucket folders under skills/.
ephemeral-sandbox CLAUDE.md
Instructions for Ephemeral-AI-Lab/ephemeral-sandbox, covering claude.md, project, engineering practice (required), build & test and sandbox tools.
code-context AGENTS.md
Instructions for infino-ai/code-context, covering code-context: notes for ai agents, project overview, repo map, build, test, gates and conventions.