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/victoriacity/openakari/claude-mdgit clone --depth 1 https://github.com/victoriacity/openakariWrote 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/victoriacity/openakari/claude-md)<a href="https://agentmods.dev/instructions/victoriacity/openakari/claude-md"><img src="https://agentmods.dev/badge/instructions/victoriacity/openakari/claude-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 | $0.04982 | $0.04982 |
| Opus 5 | $0.02491 | $0.02491 |
| Sonnet 5 | $0.00996 | $0.00996 |
| Haiku 4.5 | $0.00498 | $0.00498 |
Grade B, and why
openakari CLAUDE.md scanned grade B with 2 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 6d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
2. `curl -s -X POST http://localhost:8420/api/experiments/register -H 'Content-Type: application/json' -d '{"dir":"<abs-path>","project":"<project>","id":"<experiment-id>"}'` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. `curl -s -X POST http://localhost:8420/api/experiments/register -H 'Content-Type: application/json' -d '{"dir":"<abs-path>","project":"<project>","id":"<experiment-id>"}'` How it starts
The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this repo is
akari is a research group monorepo operated autonomously by LLM agents. The repo serves as both artifact storage and cognitive state — it is the agents' persistent memory between sessions. See docs/design.md for rationale.
Work cycle
The conversation is ephemeral; the repo is permanent. Record as you go, not at the end.
- Finding → file, immediately. When you discover a fact (data path, schema, limitation, dependency), update the relevant project file (e.g.,
existing-data.md,datasets.md) in the same turn. Do not defer recording to later. - Decision → log or decision record. When you make a choice or resolve an open question, write a log entry or decision record before moving on.
- Plan → plans/ directory. When you produce a non-trivial plan, write it to
plans/<name>.mdin the project directory. Plans in conversation history are lost. - Session summary → log entry. Before ending a session, add a dated log entry to every project README you touched, summarizing what happened and what changed.
- Open questions → README. When you identify something you can't resolve, add it to the project's
## Open questionssection.
The test: if you started a fresh session and read only the repo, would you know everything the previous session learned? If not, something is missing.
Knowledge output
akari is a research institute, not a task runner. Every plan, experiment, and session should be evaluated by the knowledge it produces — findings, decisions, hypotheses tested, questions resolved. Operational health (error rates, cost, uptime) is a supporting indicator: it measures whether the system is healthy enough to produce knowledge. The fundamental efficiency metric is findings per dollar.
Before any implementation plan, ask: "What knowledge does this produce?" If the answer is "none — it just makes the system work better," reframe: operational improvements are experiments on the system itself, and their findings ARE knowledge.
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.
- 6d ago First seen · 268 lines · 4,982 tokens per session scan B 7bab05e78e97
openakari CLAUDE.md is an instructions file published in the GitHub repository victoriacity/openakari (47 stars, last pushed 6mo ago), licensed MIT. It adds 4,982 tokens to every session, about $0.0249 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.