cliare: Instructions file for Codex

AGENTS.md

cliare AGENTS.md is an instructions file for Codex, OpenCode from modiqo/cliare. It costs 415 tokens per session, scanned A, original, Apache-2.0.

Repository-specific instructions for developing CLIARE, a Rust project with rules for code quality, architecture, resource limits, and commit hygiene.

In plain words
What is it for?
Use them when modifying CLIARE, especially when working on Rust types, traits, errors, concurrency, scoring, checkpointing, or command-line behaviour.
Why use it?
They help keep changes consistent with the project’s design documents and make errors, dependencies, runtime behaviour, and verification easier to review.

Instructions file for CodexOpenCode

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

This is modiqo/cliare's own configuration. It tells Codex and OpenCode how to work on cliare 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 cliare configures →

Reuse

Borrowing it

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

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 cliare AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/modiqo/cliare/agents-md"><img src="https://agentmods.dev/badge/instructions/modiqo/cliare/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 415 This file is loaded in full into every session.
When invoked 415 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 $0.00415 $0.00415
Opus 5.5 $0.00166 $0.00166
Sonnet 5.5 $0.00083 $0.00083
Haiku 4.5 $0.00042 $0.00042

Measured 2mo ago against content hash b92dc6b0ed66, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cliare 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 · 44 lines

What it actually says

CLIARE Agent Instructions

Quality Bar

CLIARE should be written as a world-class Rust project: clear, boring where possible, explicit where necessary, and easy for experienced Rust engineers to audit. Favor small types, narrow traits, deterministic behavior, bounded resource use, and precise errors over clever abstractions.

Implementation should follow the design packet in docs/, especially:

  • docs/model/computational-scoring-model.md
  • docs/architecture/checkpointing-and-resume.md
  • docs/architecture/rust-runtime-engineering.md
  • docs/architecture/operational-contracts.md

Rust Standards

  • Prefer explicit domain newtypes for IDs, hashes, versions, scores, and artifact references.
  • Keep traits narrow and owned by the crate that needs the abstraction.
  • Use typed errors with thiserror in library code and polished diagnostics at CLI boundaries.
  • Treat target CLI failures as evidence unless CLIARE itself failed.
  • Do not use unbounded task spawning, unbounded channels, or unbounded output buffers.
  • Do not introduce generic graph, actor, distributed execution, database, or ML dependencies without a measured need and a written rationale.
  • Keep scoring deterministic for the same evidence and model version.
  • Checkpoint and evidence-writing paths must be crash-conscious and replayable.

Commit Hygiene

  • Use Conventional Commits.
  • Do not add commit coauthor trailers.
  • Do not mention AI assistants in commit messages, code comments, docs, or generated metadata.
  • Do not add attribution comments about who authored a line or why a reviewer requested it.
  • No emojis in code, docs, commit messages, or user-facing output.

Verification

Before pushing implementation changes, run:

cargo fmt --all -- --check
env RUSTC_WRAPPER= cargo clippy --workspace --all-targets --all-features -- -D warnings
cargo test --workspace --all-features

If a command cannot run in the current environment, record the reason clearly before committing.

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 · 44 lines · 415 tokens per session scan A b92dc6b0ed66

Subscribe to this mod's changes

cliare AGENTS.md is an instructions file published in the GitHub repository modiqo/cliare (441 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 415 tokens to every session, about $0.0017 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 2026-08-30.

Related

cliare AGENTS.md compared with instructions from other repositories

cliare AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cliare AGENTS.mdmodiqo/cliareInstructions file4413mo agoApache-2.0A415Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode