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.
curl -O https://raw.githubusercontent.com/fernandogarzaaa/chimeralang-mcp/main/.claude/skills/chimera/SKILL.mdgit clone --depth 1 https://github.com/fernandogarzaaa/chimeralang-mcpWrote 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.
[](https://agentmods.dev/skills/fernandogarzaaa/chimeralang-mcp/chimera)<a href="https://agentmods.dev/skills/fernandogarzaaa/chimeralang-mcp/chimera"><img src="https://agentmods.dev/badge/skills/fernandogarzaaa/chimeralang-mcp/chimera/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.
<a href="https://agentmods.dev/skills/fernandogarzaaa/chimeralang-mcp/chimera"><img src="https://agentmods.dev/badge/skills/fernandogarzaaa/chimeralang-mcp/chimera.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00062 | $0.04340 |
| Opus 5 | $0.00031 | $0.02170 |
| Sonnet 5 | $0.00012 | $0.00868 |
| Haiku 4.5 | $0.00006 | $0.00434 |
Grade A, and why
chimera 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chimera skill — smart routing into chimeralang-mcp
Works for both Claude Code (via this SKILL.md) and Codex (via the sibling AGENTS.md adapter at repo root). Both agents end up running the same routing rules.
The chimeralang-mcp server (currently 0.8.1) exposes 51 tools. Routing all of them through every prompt is wasteful. The goal of this skill is: pick the smallest correct tool subset for the user's actual intent and execute the work through it.
Decision tree (run in order)
- Trivial input? If the prompt is
< 200chars and there are no documents/logs/messages attached, skip every chimera tool and answer directly. The token-saving hooks in.claude/settings.jsonalready handle short prompts. - Has structured payload? If the prompt or attached artifact is a document (
> 500chars), a build/test log, a long message history, or a corpus of multiple docs — go to the Routing matrix below. - Reasoning / verification request? If the user is asking for analysis, claim checking, multi-perspective deliberation, or hallucination detection — go to the Reasoning lane.
- AI-to-AI reasoning? If the user wants the agent to reason internally (without producing prose for them yet), or wants to compress a system prompt for another LLM — use the Glyph lane.
- End-of-task? Always finish with
chimera_session_reportso totals are surfaced. The Stop hook does this automatically — only call manually if you want telemetry mid-session.
Routing matrix — prompt pattern → chimera tool
| Trigger | First-choice tool | Notes |
|---|---|---|
| Single doc/code blob > 500 chars | chimera_optimize |
60–75% reduction typical; preserves fenced code with preserve_code=true. |
| Long conversation history | chimera_compress |
Proportional truncation to a token budget. |
| Both docs + history | chimera_fracture |
Single call with quality gate; prefer this over chaining the two above. |
| Build / test / install / install log | chimera_log_compress |
Errors and warnings preserved verbatim, body abridged. |
| Stable system block reused across SDK calls | chimera_cache_mark |
Lossless 75–90% via Anthropic prompt cache markers. |
| Multiple chimera calls in one go | chimera_batch |
Saves round-trips when the input is fan-out parallel. |
| Recurring per-turn cost surfacing | chimera_overhead_audit |
Quantifies "ghost tokens" (system prompt + tool defs). |
| Inspect repeated tool calls | chimera_dedup_lookup |
The PostToolUse hook populates the cache. |
| End-of-session totals | chimera_session_report |
Bundles cost summary + budget + dedup. Stop hook auto-fires. |
| LLM-free extractive summary | chimera_summarize |
Fast and deterministic; no Claude API call. |
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.
- 10d ago First seen · 269 lines · 62 tokens per session scan A 8ec07c6093b8
chimera is a skill published in the GitHub repository fernandogarzaaa/chimeralang-mcp (1 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 4,340 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.