chimera-agent AGENTS.md

chimera-agent AGENTS.md is an instructions file for Codex, OpenCode from brcampidelli/chimera-agent. It costs 960 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Chimera, a Python agent framework with a Tauri and React desktop application. They explain where project rules live and list requirements for areas such as translations, API routes, security, benchmarks, and testing.

In plain words
What is it for?
Use them as a starting point before changing Chimera code, especially the desktop interface, user-facing features, security-sensitive code, APIs, benchmarks, or tests.
Why use it?
They help contributors avoid project-specific mistakes, such as changing translation keys without care or leaving generated API types out of a route change.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/brcampidelli/chimera-agent/agents-md
Clone the repo
git clone --depth 1 https://github.com/brcampidelli/chimera-agent

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 chimera-agent AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/brcampidelli/chimera-agent/agents-md.svg)](https://agentmods.dev/instructions/brcampidelli/chimera-agent/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/brcampidelli/chimera-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/brcampidelli/chimera-agent/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 960 This file is loaded in full into every session.
When invoked 960 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00960 $0.00960
Opus 5 $0.00480 $0.00480
Sonnet 5 $0.00192 $0.00192
Haiku 4.5 $0.00096 $0.00096

Measured 4d ago against content hash ecdc61492f25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

chimera-agent 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 4d 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 · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Working in this repository

A routing document. It is short on purpose — it tells you where the real rules live and states the few that have bitten us hard enough to be worth repeating.

Chimera is a Python agent framework (chimera/) with a Tauri + React desktop app (apps/desktop/). ~41k lines of source, ~25k lines of tests, 1848 tests, mypy strict.


Where the rules live

Working on Read first
Desktop UI, styling, motion apps/desktop/DESIGN.md
Anything user-facing CONTRIBUTING.md
Security-sensitive code SECURITY.md
Benchmarks and claims bench/*/RESULTS.md and the matching PREREGISTRATION.md

Hard rules

Never rename or delete an i18n key. apps/desktop/src/lib/i18n.tsx carries every language the app offers, and the component tests assert on rendered English strings. A rename breaks them silently in all of them at once. Adding keys is free; renaming is not.

A route change and its generated types ship in the same commit. If you touch a FastAPI route in chimera/api/, regenerate both or CI fails on drift:

python -m chimera.api.schema_dump > apps/desktop/openapi.json
npm --prefix apps/desktop run gen:api

Run the full Python suite, not the module you touched. Per-module runs have let regressions reach main here before. On Windows, run it in WSL.

Never weaken a test to make it pass. If a test asserts something false, say so and rewrite it with the reasoning in the commit message — one in test_agent.py asserted that a run which called no tool had done the work. Deleting the assertion and fixing the premise look identical in a diff and are opposites in intent.

Numbers in bench/ are pre-registered. Predictions and readings are committed before a run and never loosened afterwards. A retraction is published with the same prominence as the original claim. If a result kills a claim, that is the result.

Read the full file on GitHub · 87 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. 4d ago First seen · 87 lines · 960 tokens per session scan A ecdc61492f25

Subscribe to this mod's changes

chimera-agent AGENTS.md is an instructions file published in the GitHub repository brcampidelli/chimera-agent (20 stars, last pushed today), licensed Apache-2.0. It adds 960 tokens to every session, about $0.0048 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.