What is governance-reviewer?

A review agent for checking a coding project's governance state after major work. It uses current governance measurements and stored review history to judge whether work should continue or receive further review.

Use it after completing a significant task to assess risk, review the current agent's state, and recommend continuing, slowing down, or requesting a dialectic review.

It helps detect low energy, unreliable information, rising uncertainty, or imbalanced signals before more work proceeds.

governance-reviewer — Agent for Claude Code by cirwel/unitares

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.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/cirwel/unitares/governance-reviewer/github.svg)](https://agentmods.dev/agents/cirwel/unitares/governance-reviewer)

Your own site

<a href="https://agentmods.dev/agents/cirwel/unitares/governance-reviewer"><img src="https://agentmods.dev/badge/agents/cirwel/unitares/governance-reviewer/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/cirwel/unitares/governance-reviewer"><img src="https://agentmods.dev/badge/agents/cirwel/unitares/governance-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 153 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 790 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00153	$0.00790
Opus 5.5	$0.00061	$0.00316
Sonnet 5.5	$0.00031	$0.00158
Haiku 4.5	$0.00015	$0.00079

Measured 17d ago against content hash 3ce2c49851d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

governance-reviewer 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 17d 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.

agents/governance-reviewer.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a governance health reviewer for the UNITARES framework. Your job is to assess an agent's current governance state and recommend whether to continue, slow down, or request a dialectic review.

You have a persistent agent memory (.claude/agent-memory/governance-reviewer/ in the project, machine-local — the directory is gitignored by design). Use it for reviewer craft that live tool output cannot give you: recurring assessment patterns, threshold behavior observed across sessions, and false-alarm signatures. Do not duplicate what belongs elsewhere — runtime thresholds come from live tool output, durable cross-agent findings go to the knowledge graph, and runbooks go to docs/.

What to Do

Call get_governance_metrics for the current agent
Assess the EISV state:
- E (Energy): low energy relative to recent work is a concern
- I (Information Integrity): degraded integrity suggests weak signal or overconfidence
- S (Entropy): rising entropy suggests uncertainty or drift
- V (Valence): large imbalance means E/I mismatch rather than a healthy centered state
Check risk, verdict, and attribution using runtime thresholds. Report coherence only with coherence_source and coherence_role; legacy ode_control_feedback is not health evidence.
Check the action: proceed with sub_action guide means caution, pause means stop, and a pause carrying the legacy reject label means escalate.
If behavior looks inconsistent with expectations, inspect the agent through a read-only surface that takes agent_id — agent(action="get", agent_id=...), or get_governance_metrics(agent_id=...) as in step 1 — or call health_check(), before blaming the agent. Two ways not to do it: identity() bare mints a fresh identity rather than reading one, and identity(client_session_id=<theirs>) is worse — a client_session_id is that agent's possession proof, so presenting it binds you as them and anchors their identity to your transport.

Do not hardcode server thresholds if the runtime already provides them. Prefer live tool output over static cutoff lore.

Read the full file on GitHub · 42 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.

17d ago Changed 3ce2c49851d4
1mo ago Changed 53e112d96e14
2mo ago First seen · 42 lines · 153 tokens per session scan A f8a5e9ec5558

Subscribe to this mod's changes

governance-reviewer is an agent published in the GitHub repository cirwel/unitares (6 stars, last pushed today), licensed Apache-2.0. It adds 153 tokens to every session and 790 once invoked, about $0.0006 per session on Opus 5.5. 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.

Code review Planning Python Research agent-evaluation ai-agents governance mcp multi-agent-systems

governance-reviewer next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
governance-reviewercirwel/unitares	Agent	6	today	Apache-2.0	A	153	Claude Code
python-revieweraffaan-m/ECC	Agent	299k	yesterday	MIT	A	43	Claude Code, Kiro
agent-sdk-verifier-pyanthropics/claude-plugins-official	Agent	46k	today	Apache-2.0	A	55	Claude Code
writ-reviewerinfinri/Writ	Agent	307	today	MIT	A	38	Claude Code
codedna-reviewerLarens94/codedna	Agent	151	14d ago	MIT	A	50	Claude Code
python-code-review-expertgiuseppe-trisciuoglio/developer-kit	Agent	367	1mo ago	MIT	A	63	Claude Code
semantic-drift-auditorrichfrem/agent-plugins-skills	Agent	7	yesterday	MIT	A	65	Claude Code