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/modiqo/cliare/agents-mdgit clone --depth 1 https://github.com/modiqo/cliareWhat 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 | $0.00415 | $0.00415 |
| Opus 5 | $0.00208 | $0.00208 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00042 | $0.00042 |
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 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.
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.mddocs/architecture/checkpointing-and-resume.mddocs/architecture/rust-runtime-engineering.mddocs/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
thiserrorin 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.
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 · 44 lines · 415 tokens per session scan A b92dc6b0ed66
cliare AGENTS.md is an instructions file published in the GitHub repository modiqo/cliare (487 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 415 tokens to every session, about $0.0021 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 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain 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.