agentmods.dev

unitares: Instructions file for Claude Code

CLAUDE.md

unitares CLAUDE.md is an instructions file for Claude Code from cirwel/unitares. It costs 10,434 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 for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

This is cirwel/unitares's own configuration. It tells Claude Code how to work on unitares itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything unitares configures →

not rated 6repo changed yesterday B scan 10,434 tokens original Apache-2.0
View source ↗ cirwel/unitares cirwel.org
Reuse

Borrowing it

Nothing to install: this file belongs to cirwel/unitares. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/cirwel/unitares/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/cirwel/unitares

Made for: Claude Code.

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/github.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/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for unitares CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cirwel/unitares/claude-md"><img src="https://agentmods.dev/badge/instructions/cirwel/unitares/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10,434 This file is loaded in full into every session.
When invoked 10,434 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.10434 $0.10434
Opus 5.5 $0.04174 $0.04174
Sonnet 5.5 $0.02087 $0.02087
Haiku 4.5 $0.01043 $0.01043

Measured yesterday against content hash d93ff0ae043e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 hooks** under `~/.claude/hooks/`, wired in `~/.claude/settings.json`. They are machine-local and differ per operator. On a host that wires a Watcher hook, Watcher findings at session start or in a chime bl
CLAUDE.md · 421 lines

How it starts

The opening of the file, as written. The whole thing — 421 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 hooks — hooks/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 hooks under ~/.claude/hooks/, wired in ~/.claude/settings.json. They are machine-local and differ per operator. On a host that wires a Watcher hook, 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 · 421 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 · +3 lines · +40 tokens per session d93ff0ae043e
  2. 2d ago Changed · +64 tokens per session 71a687c82899
  3. 4d ago Changed · +7 lines · +127 tokens per session dc0838a684cd
  4. 12d ago Changed · +93 tokens per session 2f0c29090c44
  5. 14d ago Changed · +2 lines · +42 tokens per session 89e52e3a8b11
  6. 15d ago Changed · +36 tokens per session 895e02ac4644
  7. 16d ago Changed · -26 tokens per session f67e0a907f1c
  8. 18d ago Changed · +9 lines · +214 tokens per session 2b32ba06ba19
  9. 19d ago Changed · +1 lines · +184 tokens per session 5287e031f6c4
  10. 22d ago First seen · 399 lines · 9,660 tokens per session scan B a09cab77cea8

Subscribe to this mod's changes

unitares CLAUDE.md is an instructions file published in the GitHub repository cirwel/unitares (6 stars, last pushed today), licensed Apache-2.0. It adds 10,434 tokens to every session, about $0.0417 per session on Opus 5.5. 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.

Building agentsMemory and contextPythonWeb3 and blockchainagent-evaluationai-agentsgovernancemcpmulti-agent-systems
Related

unitares CLAUDE.md compared with instructions from other repositories

unitares CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
unitares CLAUDE.mdcirwel/unitaresInstructions file6todayApache-2.0B10,434Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode