unitares CLAUDE.md

unitares CLAUDE.md is an instructions file for coding agents from cirwel/unitares. It costs 6,204 tokens per session, scanned B, original, Apache-2.0.

Repository instructions for unitares, including shared rules, execution-cost policy, Claude Code setup, automatic session cleanup, subagents, and memory.

In plain words
What is it for?
Use them when changing the unitares server, its CI, installers, agent configuration, or session and memory workflows.
Why use it?
They explain how the project must run without a required paid model service and keep Claude-specific rules aligned with the project's other agent instructions.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/cirwel/unitares/claude-md
Clone the repo
git clone --depth 1 https://github.com/cirwel/unitares

Wrote 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.

agentmods badge for unitares CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cirwel/unitares/claude-md.svg)](https://agentmods.dev/instructions/cirwel/unitares/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cirwel/unitares/claude-md"><img src="https://agentmods.dev/badge/instructions/cirwel/unitares/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,204 This file is loaded in full into every session.
When invoked 6,204 The same file — it is already loaded in full.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.06204 $0.06204
Opus 5 $0.03102 $0.03102
Sonnet 5 $0.01241 $0.01241
Haiku 4.5 $0.00620 $0.00620

Measured yesterday against content hash 5b05958a502a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

unitares CLAUDE.md scanned grade B with 1 finding 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 yesterday.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **User-level `~/.claude/hooks/`**, wired in `~/.claude/settings.json` (auto-test, watcher-hook, watcher-chime, stop-milestone-audit, …). Watcher findings at session start or in a chime block come from this chain, not f
CLAUDE.md · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — unitares

Bootstrap for Claude Code sessions in this repo. Content below the SHARED CONTRACT markers is kept byte-identical with AGENTS.md — CI (scripts/dev/check-shared-contract.sh) enforces parity. Edit shared rules in both files; edit the Claude preamble here only.

The installable Codex/Claude adapter bundle is canonical in the companion unitares-governance-plugin repo. This file only governs how Claude Code should behave while working directly inside the unitares server repo.

Claude-specific wiring

Claude Code runs through a plugin-style harness. The hook lifecycle is owned by the unitares-governance-plugin repo (canonical for the adapter bundle); this repo vendors no hook chain of its own. When CLAUDE.md or AGENTS.md describes hook behavior, the plugin is the source of truth.

Three layers fire on Claude lifecycle events, and it matters which one produced what you are looking at:

  • Plugin hookshooks/session-start, hooks/post-edit, hooks/post-stop. The per-turn check-in is the plugin's post-stop, which submits epistemic_class="substrate_interpretation" for both Claude and Codex: a substrate reading of turn shape, not an agent-authored report.
  • User-level ~/.claude/hooks/, wired in ~/.claude/settings.json (auto-test, watcher-hook, watcher-chime, stop-milestone-audit, …). Watcher findings at session start or in a chime block come from this chain, not from the plugin's post-edit.
  • A file on disk under hooks/ is not evidence that it runs. Retired hooks stay on disk; check settings.json before assuming a user-level hook is live.

To close a Watcher finding (the agent itself lives in this repo):

python3 agents/watcher/agent.py --resolve <fingerprint>   # confirmed bug, fixed
python3 agents/watcher/agent.py --dismiss <fingerprint>   # false positive

Reference fingerprints in the commit message — Watcher's audit trail lives in commits, not in tracked files (data/watcher/ is gitignored).

Read the full file on GitHub · 316 lines

Changes

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.

  1. yesterday Changed · -17 lines · -713 tokens per session 5b05958a502a
  2. 5d ago First seen · 333 lines · 6,917 tokens per session scan B e166b3b3fa50

Subscribe to this mod's changes

unitares CLAUDE.md is an instructions file published in the GitHub repository cirwel/unitares (4 stars, last pushed today), licensed Apache-2.0. It adds 6,204 tokens to every session, about $0.0310 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.