What is chimeralang-mcp AGENTS.md?

A Codex-specific instruction guide for chimeralang-mcp, the server that provides tools for reducing and managing large model inputs. It maps common request types to exact tool names, arguments, and verification rules.

Use it in the chimeralang-mcp repository when handling large documents, code, conversations, logs, cached instructions, reasoning tasks, or session reports.

It gives Codex a clear way to decide when these tools are needed and how to call them correctly, while identifying cases where they should be skipped.

How fernandogarzaaa/chimeralang-mcp configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to fernandogarzaaa/chimeralang-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.

Copy the file

curl -O https://raw.githubusercontent.com/fernandogarzaaa/chimeralang-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/fernandogarzaaa/chimeralang-mcp

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/fernandogarzaaa/chimeralang-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/fernandogarzaaa/chimeralang-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/fernandogarzaaa/chimeralang-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/fernandogarzaaa/chimeralang-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/fernandogarzaaa/chimeralang-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/fernandogarzaaa/chimeralang-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,264 This file is loaded in full into every session.

When invoked 2,264 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.

Model	Per session	Once invoked
Fable 5.1	$0.02264	$0.02264
Opus 5.5	$0.00906	$0.00906
Sonnet 5.5	$0.00453	$0.00453
Haiku 4.5	$0.00226	$0.00226

Measured 24d ago against content hash 55ba3818f638, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chimeralang-mcp 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 24d 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 · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Agent Guide — chimeralang-mcp

chimera_version: 0.8.4 — keep this in sync with pyproject.toml and .claude/skills/chimera/SKILL.md.

This file is the Codex-readable adapter of the chimera skill. The canonical version lives at .claude/skills/chimera/SKILL.md; this is the same routing matrix in the location Codex actually walks.

When Codex is operating inside this repository, follow these rules.

When to invoke chimeralang-mcp

The chimeralang-mcp server (currently 0.8.4) exposes 51 tools. Pick the smallest correct subset for the user's actual intent — never invoke all of them.

Skip chimera tools entirely if:

Prompt is < 200 chars and has no attached document/log/history.
The user is debugging chimeralang-mcp itself (don't pre-compress the thing you're trying to read).
The user is asking a meta question about tools (definitions, schemas).
The user said "skip chimera" or "raw output only".

Engage chimera tools otherwise — the cost-saving compounds quickly.

Routing matrix — prompt pattern → tool

Trigger	First-choice tool	Notes
Single doc/code blob > 500 chars	`chimera_optimize`	60–75% reduction; pass `preserve_code=true` to keep fenced blocks.
Long conversation history	`chimera_compress`	Proportional truncation.
Both docs + history	`chimera_fracture`	One call, quality gate, prefer over chaining.
Build/test/install log	`chimera_log_compress`	Errors/warnings verbatim, body abridged.
Stable system block reused across SDK calls	`chimera_cache_mark`	Lossless 75–90% via Anthropic prompt cache.
Multiple chimera calls at once	`chimera_batch`	Saves round-trips.
Recurring per-turn cost surfacing	`chimera_overhead_audit`	Quantifies system-prompt + tool-def overhead.
Inspect repeated tool calls	`chimera_dedup_lookup`	Populated by the PostToolUse hook.
End-of-session totals	`chimera_session_report`	Already auto-fired by Stop hook.
LLM-free extractive summary	`chimera_summarize`	Deterministic, no API call.

Read the full file on GitHub · 181 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.

24d ago Changed 55ba3818f638
1mo ago Changed 7964e69749e9
1mo ago Changed 9f42468ddbd8
2mo ago First seen · 181 lines · 2,264 tokens per session scan A 7b2aff397fb3

Subscribe to this mod's changes

chimeralang-mcp AGENTS.md is an instructions file published in the GitHub repository fernandogarzaaa/chimeralang-mcp (1 stars, last pushed 6d ago), licensed MIT. It adds 2,264 tokens to every session, about $0.0091 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 agents

chimeralang-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
chimeralang-mcp AGENTS.mdfernandogarzaaa/chimeralang-mcp	Instructions file	1	6d ago	MIT	A	2,264	Claude Code, Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

chimeralang-mcp: Instructions file for Claude Code