Borrowing it
Nothing to install: this file belongs to fabio-rovai/brain-in-the-fish. 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/fabio-rovai/brain-in-the-fish/main/CLAUDE.mdgit clone --depth 1 https://github.com/fabio-rovai/brain-in-the-fishWrote 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/instructions/fabio-rovai/brain-in-the-fish/claude-md)<a href="https://agentmods.dev/instructions/fabio-rovai/brain-in-the-fish/claude-md"><img src="https://agentmods.dev/badge/instructions/fabio-rovai/brain-in-the-fish/claude-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.
<a href="https://agentmods.dev/instructions/fabio-rovai/brain-in-the-fish/claude-md"><img src="https://agentmods.dev/badge/instructions/fabio-rovai/brain-in-the-fish/claude-md.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 | $0.00569 | $0.00569 |
| Opus 5.5 | $0.00228 | $0.00228 |
| Sonnet 5.5 | $0.00114 | $0.00114 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
brain-in-the-fish CLAUDE.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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brain in the Fish
Score any document. Prove every claim. The LLM decomposes documents into OWL knowledge graphs, SPARQL rules mine facts from the graph, and a gate verifies the score is consistent with the evidence.
Relationship to open-ontologies
This project depends on open-ontologies as a library (../open-ontologies). It uses the ontology engine (GraphStore, Reasoner, SPARQL) to load and query document argument graphs. It is NOT a fork — it consumes open-ontologies as a dependency.
Module Overview
| Module | Purpose |
|---|---|
types |
Core evaluation domain types |
ingest |
PDF ingestion and document ontology generation |
criteria |
Evaluation criteria ontology loading/generation |
agent |
Agent cognitive model and spawning |
scoring |
Independent scoring engine with ReACT loop |
debate |
Multi-round structured debate orchestrator |
moderation |
Consensus moderation and convergence detection |
report |
Evaluation report generation |
gate |
Verdict system — CONFIRMED/FLAGGED/REJECTED based on evidence |
rules |
SPARQL rule mining over argument graphs (8 rules) |
argument_graph |
OWL Turtle → typed argument graph with structural metrics |
server |
MCP server exposing eval_* and eds_* tools |
snn |
Deprecated — legacy scoring, use gate module instead |
Pipeline
- LLM reads document → produces OWL Turtle (typed nodes with source quotes)
- Turtle loads into GraphStore → structural metrics extracted via SPARQL
- SPARQL INSERT rules derive facts (StrongClaim, UnsupportedClaim, etc.)
- Gate compares LLM holistic score against structural + quality evidence
- Verdict: CONFIRMED / FLAGGED / REJECTED
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.
- 2mo ago First seen · 57 lines · 569 tokens per session scan A a3dec5f88298
brain-in-the-fish CLAUDE.md is an instructions file published in the GitHub repository fabio-rovai/brain-in-the-fish (97 stars, last pushed 2mo ago), licensed MIT. It adds 569 tokens to every session, about $0.0023 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.
brain-in-the-fish CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| brain-in-the-fish CLAUDE.mdfabio-rovai/brain-in-the-fish | Instructions file | 97 | 2mo ago | MIT | A | 569 | Claude Code |
| 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 |