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/arkon-ai/arkon/claude-mdgit clone --depth 1 https://github.com/arkon-ai/arkonWrote 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/arkon-ai/arkon/claude-md)<a href="https://agentmods.dev/instructions/arkon-ai/arkon/claude-md"><img src="https://agentmods.dev/badge/instructions/arkon-ai/arkon/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 | $0.01839 | $0.01839 |
| Opus 5 | $0.00920 | $0.00920 |
| Sonnet 5 | $0.00368 | $0.00368 |
| Haiku 4.5 | $0.00184 | $0.00184 |
Grade A, and why
arkon 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 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project-level context for Claude Code sessions in this repo.
Coding Doctrine v2
Canonical: warden-memory/docs/coding-doctrine-v2.md. Inlined here so it
loads even when warden-memory isn't on the host.
These rules apply to every task in this repo unless explicitly overridden. Bias: caution over speed on non-trivial work. Use judgment on trivial tasks.
Rule 1 — Think before coding
State assumptions explicitly. If uncertain, ask rather than guess. Present multiple interpretations when ambiguity exists. Push back when a simpler approach exists. Stop when confused. Name what's unclear.
Rule 2 — Simplicity first
Minimum code that solves the problem. Nothing speculative. No features beyond what was asked. No abstractions for single-use code. Test: would a senior engineer say this is overcomplicated? If yes, simplify.
Rule 3 — Surgical changes
Touch only what you must. Clean up only your own mess. Don't "improve" adjacent code, comments, or formatting. Don't refactor what isn't broken. Match existing style.
Rule 4 — Goal-driven execution
Define success criteria up front. Loop until verified. Don't follow steps — define success and iterate. Strong success criteria let you loop independently.
Rule 5 — Use the model only for judgment calls
Use me for: classification, drafting, summarization, extraction. Do NOT use me for: routing, retries, deterministic transforms. If code can answer, code answers.
Rule 6 — Fetch current docs before touching external code
Before writing or editing code that calls any external library, SDK, CLI, or cloud service: fetch current docs (Context7, official site, or library README). Your training data is frozen; the library is not. Skip only for: refactors within established patterns, internal APIs, code review, general programming concepts.
Rule 7 — Surface conflicts, don't average them
If two patterns contradict, pick one (more recent / more tested). Explain why. Flag the other for cleanup. Don't blend conflicting patterns to "feel 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 · 136 lines · 1,839 tokens per session scan A 95d48abc3498
arkon CLAUDE.md is an instructions file published in the GitHub repository arkon-ai/arkon (5 stars, last pushed yesterday), licensed MIT. It adds 1,839 tokens to every session, about $0.0092 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
decapod CLAUDE.md
Claude Code instructions for DecapodLabs/decapod, covering claude.md - agent entrypoint, orientation & documentation, mandatory prompt safety gate, project context and quick start.
VaultysClaw agent-controller.instructions.md
Use when working on the agent-controller package: tools, skills, agent runtime, WebSocket client, local SQLite DB, LLM integration, or CLI modes.
open-ace CLAUDE.md
Claude Code instructions for open-ace/open-ace, covering claude.md, where process documents go, pushing, test placement and ci semantics and schema snapshots (schema-sync ci).
claude-skills CLAUDE.md
Instructions for mastepanoski/claude-skills, covering claude.md, repository purpose, testing skills locally, repository architecture and core structure.
runtm copilot-instructions.md
Copilot instructions for runtm-ai/runtm, covering runtm tool instructions, critical rules, structure, adding endpoints and app/api/v1/myendpoint.py.
ai-act-skills AGENTS.md
Instructions for abk1969/ai-act-skills, covering agents.md — ai-act-skills, skill provided by this repository, recommended install location, how a codex / agents-aware host should activate the skill and tool-name mapping.