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/larens94/codedna/claude-mdgit clone --depth 1 https://github.com/Larens94/codednaWhat 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 | $0.02847 | $0.02847 |
| Opus 5 | $0.01424 | $0.01424 |
| Sonnet 5 | $0.00569 | $0.00569 |
| Haiku 4.5 | $0.00285 | $0.00285 |
Grade A, and why
codedna 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 3d 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.
This is a copy
88% identical to codedna AGENTS.md — 40 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeDNA v0.9 — Protocol for Claude Code
This project uses the CodeDNA in-source communication protocol. Follow these rules on every file operation.
Reading files
- Read the CodeDNA module header at the top of every supported source file before reading any code. Python uses a module docstring; other languages use their native comment syntax.
- Parse
exports:— these are symbols you must never rename or remove without explicit instruction. - Parse
used_by:— callers that depend on this file. Do not follow all of them blindly. Ask: "does this caller's domain intersect with my current task?" Only explore callers relevant to the specific change you're making. - Parse
related:— files sharing the same logic without importing each other. Same filter: is it relevant to this task? - Parse
rules:— hard constraints for every edit in this file; read before writing any logic. - Parse
agent:— session history written by previous agents; read to understand why the current state exists. - For any function with a
Rules:docstring, read and respect those before writing logic.
Required audit workflow
- Onboarding: run
codedna doctor --path .; resolve errors before editing. - Before public changes: run
codedna impact <file-or-symbol> --path .; read matching rules and relevant affected callers. - After structural edits: run
codedna verify .. Exit 1 means review evidence, runcodedna refresh ., then verify again. - Use
--jsonin automation.verifyproves structural fields only, never semantic truth ofrules:.
Writing new files
Every new source file must begin with a CodeDNA header in its native syntax. Python uses this canonical module docstring:
"""filename.py — <what it does, ≤15 words>.
exports: public_function(arg) -> return_type
used_by: consumer_file.py → consumer_function
related: other_file.py — shares same pattern/logic (no import link)
wiki: docs/wiki/filename.md
rules: <hard constraint agents must never violate>
agent: <your-model-id> | <provider> | <YYYY-MM-DD> | <session_id> | <what you implemented and what you noticed>
message: "<open hypothesis or observation for the next agent>"
"""
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.
- 3d ago First seen · 258 lines · 2,847 tokens per session scan A 56f459d836f4
codedna CLAUDE.md is an instructions file published in the GitHub repository Larens94/codedna (145 stars, last pushed 6d ago), licensed MIT. It adds 2,847 tokens to every session, about $0.0142 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to codedna AGENTS.md, differing in 40 lines, and is treated as a copy.
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.