agentmods.dev

clibridge: Instructions file for Codex

AGENTS.md

clibridge AGENTS.md is an instructions file for Codex, OpenCode from mateusoliveirab/clibridge. It costs 544 tokens per session, scanned A, original, MIT.

A repository guide for coding agents working on Clibridge, a tool that routes tasks between different command-line AI assistants. It maps the codebase and lists rules agents must follow.

In plain words
What is it for?
Use it to find important folders, understand contribution rules, and run the required checks when working on Clibridge.
Why use it?
It gives an agent the project context and constraints before it changes code, reducing guesswork and unsafe edits.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is mateusoliveirab/clibridge's own configuration. It tells Codex and OpenCode how to work on clibridge itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything clibridge configures →

not rated 0repo 2mo ago A scan 544 tokens original MIT
View source ↗ mateusoliveirab/clibridge
Reuse

Borrowing it

Nothing to install: this file belongs to mateusoliveirab/clibridge. 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/mateusoliveirab/clibridge/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/mateusoliveirab/clibridge

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.

agentmods badge for clibridge AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mateusoliveirab/clibridge/agents-md/github.svg)](https://agentmods.dev/instructions/mateusoliveirab/clibridge/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mateusoliveirab/clibridge/agents-md"><img src="https://agentmods.dev/badge/instructions/mateusoliveirab/clibridge/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.

agentmods 80×15 button for clibridge AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mateusoliveirab/clibridge/agents-md"><img src="https://agentmods.dev/badge/instructions/mateusoliveirab/clibridge/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 544 This file is loaded in full into every session.
When invoked 544 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00544 $0.00544
Opus 5.5 $0.00218 $0.00218
Sonnet 5.5 $0.00109 $0.00109
Haiku 4.5 $0.00054 $0.00054

Measured 2mo ago against content hash 13d536c1263d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

clibridge 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 2mo 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.

AGENTS.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Clibridge contributor guide for coding agents

This is the tool-neutral entry point for AI contributors. Read this file before changing code; use CONTRIBUTING.md for the human workflow and docs/architecture.md for the system contract.

When present, also read agents.local.md. It defines the delegated maintainer operating mode and the routing policy for this checkout. It may authorize routine in-scope execution, but it never weakens the non-negotiable rules below or external platform protections.

Repository map

  • src/adapters/ — provider-specific command construction and capability checks.
  • src/broker/ — routing, normalized errors, schema validation, and dispatch.
  • src/daemon/ — localhost-only control plane, SQLite ledger, approvals, SSE, and secret redaction.
  • src/workflows/ — workflow parsing, execution, and contribution policy.
  • dashboard/ — local operator console; it shares the daemon API and ledger.
  • test/ — offline node:test suite. Keep tests in this directory so the test command cannot accidentally collect nested worktrees.

Non-negotiable rules

  1. Never persist, log, or display raw credentials, tokens, prompts containing secrets, or unredacted provider output. Use the redaction boundary in src/daemon/redaction.ts.
  2. Diagnostics and live validation must set disableFallback: true; a fallback may hide an authentication, credit, or provider failure.
  3. New provider behavior requires an adapter contract, capability validation, offline tests, and a documented live-validation command when a local binary is involved.
  4. New daemon mutations must retain project scoping, the approval gate for risky work, ledger evidence, and the shared src/daemon/client.ts path.
  5. Do not publish packages, push branches, reset/clean Git state, or alter credentials without explicit user or maintainer authorization.

Required validation

Run npm run ci before opening a pull request. It runs TypeScript, the build, the scoped offline test suite, and the dry-run smoke check. Run a relevant live:validate:* command only when its provider binary and credentials are available; never treat a skipped live check as proof.

Read the full file on GitHub · 48 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.

  1. 2mo ago First seen · 48 lines · 544 tokens per session scan A 13d536c1263d

Subscribe to this mod's changes

clibridge AGENTS.md is an instructions file published in the GitHub repository mateusoliveirab/clibridge (0 stars, last pushed 2mo ago), licensed MIT. It adds 544 tokens to every session, about $0.0022 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 2026-08-31.

Building agentsWriting and docs
Related

clibridge AGENTS.md compared with instructions from other repositories

clibridge AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
clibridge AGENTS.mdmateusoliveirab/clibridgeInstructions file02mo agoMITA544Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode