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/nimocat/fishbowl/agents-mdgit clone --depth 1 https://github.com/nimocat/fishbowlWrote 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/nimocat/fishbowl/agents-md)<a href="https://agentmods.dev/instructions/nimocat/fishbowl/agents-md"><img src="https://agentmods.dev/badge/instructions/nimocat/fishbowl/agents-md.svg" alt="Measured on agentmods" 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 | $0.00310 | $0.00310 |
| Opus 5 | $0.00155 | $0.00155 |
| Sonnet 5 | $0.00062 | $0.00062 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
fishbowl 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 5d 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
Agent Instructions
- Keep
docs/agent-log.md,docs/implementation-plan.md,CONTEXT.md, ADRs, anddocs/handoff.mdcurrent during substantial work. - Follow test-driven development for behavior changes.
- Keep SQLite project scoping explicit in every query and mutation.
- Never persist raw logs, environment values, or unredacted excerpts in SQLite.
- Run
npm run typecheck,npm test, andnpm run buildbefore declaring completion. - After completing a Fishbowl upgrade, refresh the local linked installation and current-user daemon registration, then verify the updated daemon through direct Fishbowl MCP before declaring completion. Preserve local knowledge data and the configured fixed port.
Fishbowl Access From Codex
- Use direct Fishbowl MCP tool calls for all agent queries and writes.
- Never fall back to the Fishbowl CLI,
node .../dist/cli/main.js, direct SQLite access, or shell wrappers when MCP is unavailable. - Treat MCP tool discovery as the only Fishbowl discovery path. Do not search PATH, package scripts, or the filesystem for a Fishbowl CLI executable from an agent session.
- Treat the CLI as a human-operated installation, diagnostics, and recovery interface only.
- If the MCP namespace or required tool is unavailable, report it and ask the user to configure or restart the MCP client. Do not substitute another transport; continue the core task only when omitting Fishbowl persistence is safe.
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.
- 5d ago First seen · 20 lines · 310 tokens per session scan A 110aaa3c568b
fishbowl AGENTS.md is an instructions file published in the GitHub repository nimocat/fishbowl (0 stars, last pushed 1mo ago), licensed MIT. It adds 310 tokens to every session, about $0.0015 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 instructions, from other repositories
kernal CLAUDE.md
Instructions for pintomatic/kernal, covering kernal — developer guide, what this is, architecture, stack and project structure.
gitnodes AGENTS.md
AGENTS.md instructions for AndreaBozzo/gitnodes, covering agents.md, what this is, commands, architecture and invariants and gotchas.
gitnodes CLAUDE.md
Claude Code instructions for AndreaBozzo/gitnodes: Contributor and agent guidance for this repository lives in AGENTS.md, the tool-neutral source of truth. Claude Code imports it here so it loads automatically.
codeGraph-branch CLAUDE.md
Instructions for lagrahhn/codeGraph-branch, covering claude.md, project overview, build, test, run, single test file / pattern and architecture.
m_flow AGENTS.md
AGENTS.md instructions for FlowElement-xinliuyuansu/m_flow, covering m-flow — developer & agent reference, 1. repository map, extension points, 2. local development and python backend (requires python 3.10 – 3.13).
llm-wiki-agent GEMINI.md
Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.