Borrowing it
Nothing to install: this file belongs to JoaoBerne/cli-bridge-mcp. 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/JoaoBerne/cli-bridge-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/JoaoBerne/cli-bridge-mcpWrote 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/joaoberne/cli-bridge-mcp/agents-md)<a href="https://agentmods.dev/instructions/joaoberne/cli-bridge-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/joaoberne/cli-bridge-mcp/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/joaoberne/cli-bridge-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/joaoberne/cli-bridge-mcp/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 | $0.01315 | $0.01315 |
| Opus 5.5 | $0.00526 | $0.00526 |
| Sonnet 5.5 | $0.00263 | $0.00263 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
cli-bridge-mcp AGENTS.md scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
bridges/ # openai_compatible.py = cli-bridge-openai (urllib only; used by the applepcc lane and HTTP lanes) How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guide — cli-bridge
Guidance for AI coding agents (Claude Code, Codex, Gemini CLI, opencode…) working on this
repo. CLAUDE.md is a symlink to this file.
What this is
An MCP server that exposes the other AI CLIs on the machine as tools. Each lane spawns
the official CLI as a subprocess (no token extraction, no API keys). Read-only by
default. Pure-stdlib + mcp only. Default surface: 15 fixed tools + ask_<lane> per installed
CLI (schemas.DEFAULT_TOOLS, CLI_BRIDGE_TOOLS to widen).
Layout
src/cli_bridge/
server.py # MCP surface: handlers, call_tool dispatch, hot path (_run_lane incl. spend gates), _run_workflow_preset table. Keep thin.
mcp_compat.py # the ONLY file that branches on the mcp SDK major (1.x decorators vs 2.x add_request_handler, renamed fields)
schemas.py # tool schemas (_tools_for/_ask_schema, shared _P params, DEFAULT_TOOLS + _filter_tools) — pure
reports.py # doctor/doctor_deep + _render_* markdown + setup recommendation (injected is_host/run_lane)
prompts.py # MCP prompts (apilookup)
resources.py # MCP resources: config, lane-stats, usage-summary (pure)
lanes.py # LaneSpec registry + argv builders + custom-lane JSON loader + PATH detection + model probes
runner.py # subprocess exec, redaction, ANSI cleanup, process-tree kill, error classification, pacing, streaming
config.py # env parsing (lane_env* for CLI_BRIDGE_<LANE>_*), cost profile, timeouts, INSTRUCTIONS
telemetry.py # sqlite3 run log + lane health/cooldown + cache + ratings/lessons (best-effort)
router.py # deterministic cascade / ask_best ordering (pure)
council.py # ask_all/ask_cascade/ask_best/synthesize fan-out (injected run_lane)
jobs.py # in-process async jobs (job tool) + sqlite persistence
workflows.py # review_diff (focus=code|security), debate (vote=judge|borda), premortem, test_plan, challenge, git_text, prechecks
orchestrate.py # batch_run durable fan-out + presets refine_plan/map_review/research_verify/fanout_compare/converge
findings.py # parse/merge/render structured review findings (pure)
guards.py # injection/tool-poisoning output guard (CLI_BRIDGE_GUARD)
worktrees.py # ask_build (isolated worktree diff | direct zone-guarded write, in-process zone lock, artifact return)
buildloop.py # steerable multi-turn direct builds: job action=tail|steer, executable DoD gate
conversations.py # round-table threads: sqlite transcript + recipient-aware replay + rolling summary
preamble.py # terse response-style preamble prepended to delegate prompts
cli.py # human/CI entry point (cli-bridge ...) over the same internals
bridges/ # openai_compatible.py = cli-bridge-openai (urllib only; used by the applepcc lane and HTTP lanes)
tests/ # pytest; unit + cross-host integration (no real CLI needed)
benchmarks/ # eval harness (several models vs one), outside the package and CI: eval.py, tests/, fixtures/evalset/
docs/ # TOOLS, ARCHITECTURE, HOSTS, BUDGET, COSTS
examples/ # lane JSON recipes (local-runtime, apple-fm-serve, openai-compatible, community, free-apis), mcp.example.json, local-first-host.md
plugin/ # Claude Code plugin manifest (wires the MCP server; no skills)
assets/ # README banner/mark/social (generated, do not hand-edit)
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.
- 1mo ago Changed · -63 lines · -1,205 tokens per session de5c56c0c890
- 2mo ago First seen · 141 lines · 2,520 tokens per session scan A b53c476dfb9c
cli-bridge-mcp AGENTS.md is an instructions file published in the GitHub repository JoaoBerne/cli-bridge-mcp (2 stars, last pushed 17d ago), licensed Apache-2.0. It adds 1,315 tokens to every session, about $0.0053 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.