governance-fundamentals

governance-fundamentals is a skill for Claude Code, Codex from cirwel/unitares. It costs 53 tokens per session (3,939 once invoked), scanned A, original, Apache-2.0.

Reference material for UNITARES, a system that estimates an AI agent's working state and whether it is drifting from its normal pattern. It explains measures for energy, information accuracy, instability, and emotional direction.

In plain words
What is it for?
Use it when reading UNITARES check-ins, governance metrics, state vectors, policy actions, coherence, or calibration results.
Why use it?
It prevents governance measurements from being mistaken for final judgments about whether work succeeded. It also explains how to interpret the measurements when little or no history exists.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when reading UNITARES check-ins, governance metrics, state vectors, policy actions, coherence, or calibration results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cirwel/unitares/governance-fundamentals
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.

Any agent
npx skills add cirwel/unitares --skill governance-fundamentals
Clone the repo
git clone --depth 1 https://github.com/cirwel/unitares

Made for: Claude Code, Codex.

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 governance-fundamentals

README.md
[![agentmods](https://agentmods.dev/badge/skills/cirwel/unitares/governance-fundamentals/github.svg)](https://agentmods.dev/skills/cirwel/unitares/governance-fundamentals)
Your own site
<a href="https://agentmods.dev/skills/cirwel/unitares/governance-fundamentals"><img src="https://agentmods.dev/badge/skills/cirwel/unitares/governance-fundamentals/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 governance-fundamentals

Your own site · 80×15
<a href="https://agentmods.dev/skills/cirwel/unitares/governance-fundamentals"><img src="https://agentmods.dev/badge/skills/cirwel/unitares/governance-fundamentals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,939 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.03939
Opus 5 $0.00026 $0.01969
Sonnet 5 $0.00011 $0.00788
Haiku 4.5 $0.00005 $0.00394

Measured today against content hash 7bd24fe45ae8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

governance-fundamentals 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 today.

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.

skills/governance-fundamentals/SKILL.md · 235 lines

How it starts

The opening of the file, as written. The whole thing — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Governance Fundamentals

What UNITARES Is

UNITARES provides digital proprioception for AI agents — awareness of your own state, your relationship to the system, and whether you are drifting. The live path is behavioral state estimation: observable work signals become EISV readings, smoothed over time and compared with the agent's own trajectory once a baseline exists. The thermodynamic / ODE model remains useful as a research lens and telemetry; do not present it as cold-start authority or live verdict authority.

EISV State Vector

Every agent has four dimensions, updated through check-ins:

Dimension Range Meaning
E (Energy) [0, 1] Productive capacity
I (Information Integrity) [0, 1] Claims matching results / calibration
S (Entropy) [0, 1] Drift / instability from normal (lower is usually steadier)
V (Valence) [-1, 1] EMA-smoothed E-I imbalance

How the Live Path Reads Them

  • E (Energy) currently blends decision success, complexity calibration, sometimes external task evidence, and a legacy coherence-level term sourced from legacy_tanh_v ODE control feedback. That last input is compatibility debt, not behavioral health evidence.
  • I (Integrity) currently blends calibration/outcome consistency with the trend of that same legacy controller scalar. Read it as a deployed heuristic, not a pure claims-match-results measurement.
  • S (Entropy / drift) rises with drift norm, regime instability, and complexity divergence.
  • V (Valence) is derived from the E-I imbalance. Positive means running hot (motion outruns integrity); negative means running careful (integrity outruns progress).

The headline math is proprioceptive residuals. The live authority stages are explicit: check-ins 1–2 use the mostly server-derived Φ cold-start prior; check-ins 3–24 use the behavioral assessment against fixed universal thresholds; check-in 25 enables self-relative z-score deviation against the agent's Welford baseline (the stage boundaries derive from BEHAVIORAL_AUTHORITY_THRESHOLD = 0.3 over BOOTSTRAP_UPDATES = 10, and is_baselined at baseline_confidence >= 0.8 with the confidence ramp (update_count - 5) / 25). Absolute safety floors and basin-health gates remain in force throughout.

Read the full file on GitHub · 235 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. today Changed 7bd24fe45ae8
  2. yesterday Changed 0882c59b8879
  3. 2d ago Changed · +3 lines 20b81e7a89af
  4. 3d ago Changed · +39 lines e827c96547a0
  5. 11d ago First seen · 193 lines · 53 tokens per session scan A 4c23d13e5d85

Subscribe to this mod's changes

governance-fundamentals is a skill published in the GitHub repository cirwel/unitares (4 stars, last pushed today), licensed Apache-2.0. It adds 53 tokens to every session and 3,939 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

adk-agent-builder

Builds ADK (Agent Development Kit) Python agents: LLM agents with tools, graph workflows of function and agent nodes, conditional routing, fan-out and join, schema-validated delegation between agents, human-in-the-loop pauses, and pytest coverage for all of it. Use when asked to create an agent or a workflow, add a…

google/adk-python · 177 tokens

adk-style

Python style and codebase conventions for ADK (Agent Development Kit): private-by-default file visibility, imports, type hints, Pydantic v2 models, formatting, docstrings, logging, async I/O, file and test layout, and unit test structure. Use when writing or editing ADK source or tests, deciding whether a new file or…

google/adk-python · 187 tokens

adk-verify-snippets

Checks that every Python code block in a Markdown file actually compiles and runs, by extracting each block to a temporary file, executing it in an isolated subprocess, and writing a pass/fail report with per-snippet coverage. Use when the user asks to verify, test, or validate the code samples in a README, a guide…

google/adk-python · 149 tokens

adk-setup

Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test run. Runs only when explicitly requested, never on its own. Use when asked to set up, bootstrap, or repair a development…

google/adk-python · 146 tokens

python-best-practices

Provides Python patterns for type-first development with dataclasses, discriminated unions, NewType, and Protocol. Must use when reading or writing Python files.

NoesisVision/nasde-toolkit · 36 tokens

Python Data Analysis

Clean datasets and create reproducible Python transformations and charts.

Raidriar7170/hermes-skilleval · 15 tokens