What is writing-governance-records?

A writing procedure for documenting how one AI workflow is governed. The record covers ownership, process, components, evaluations, operating steps, and how changes are approved.

Use it when creating or updating a governance record for an AI workflow. It produces a Markdown record showing the status, evidence, and gaps for eight governance practices.

It turns missing governance practices into explicit follow-up actions instead of leaving them implicit. This gives reviewers evidence of how the workflow is built, checked, operated, and changed.

writing-governance-records — Skill for Claude Code by jamesgray-ai

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 jamesgray-ai/handsonai-plugins --skill writing-governance-records

Clone the repo

git clone --depth 1 https://github.com/jamesgray-ai/handsonai-plugins

Made for: Claude Code.

Or install handsonai, the plugin that ships this one along with the rest of its 16 skills.

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/skills/jamesgray-ai/handsonai-plugins/writing-governance-records/github.svg)](https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/writing-governance-records)

Your own site

<a href="https://agentmods.dev/skills/jamesgray-ai/handsonai-plugins/writing-governance-records"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/writing-governance-records/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/skills/jamesgray-ai/handsonai-plugins/writing-governance-records"><img src="https://agentmods.dev/badge/skills/jamesgray-ai/handsonai-plugins/writing-governance-records.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 187 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,238 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	$0.00187	$0.03238
Opus 5.5	$0.00075	$0.01295
Sonnet 5.5	$0.00037	$0.00648
Haiku 4.5	$0.00019	$0.00324

Measured yesterday against content hash 5de86a27d0e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

writing-governance-records 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 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.

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.

plugins/handsonai/skills/writing-governance-records/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Governance Records

Write a governance record for one AI workflow: one Markdown file that shows, for each of the eight governance practices, whether the workflow has it, the evidence, and the follow-up action for each gap. A company's AI governance policy says where every workflow should stand; the record shows where this one does, and the policy's reviews read it. The file's shape is in references/record-format.md.

The eight practices, in two groups:

Register it (what the workflow is and where it lives): 1 name and description, 2 ownership (a team, not a person), 3 process (what comes before and after it).
Control it (how it's built, checked and changed): 4 building blocks (its skills, agents, and the systems and files it touches), 5 evaluations (tests for the skills, the agents and the whole workflow), 6 SOP (how it runs, written for people), 7 operations (when it runs and where its outputs go), 8 change management (who approves a change and how it reaches the team).

Workflow

Entry

Find the working folder: the folder that holds registry/ and framework/. On Claude Code and Codex it's the workspace; on Claude desktop, the folder the user selected; on the web and in Microsoft 365, ai-workspace/ (or the user's own working folder) in their drive, read through the connection. Read only inside it. If you can't read any files, ask the user to select or connect their working folder; until then, read and save nothing.
Find the workflow by the name the user gave: its registry entry registry/workflows/[slug].md and its folder framework/[slug]/. If the name could be more than one workflow, or none and the user hasn't said it's outside their files:

Ask: "Which workflow is this for?" (List the registry's workflow titles when there are a few; otherwise ask for its name.)

"Not sure" or a name that matches nothing: write the record from the user's answers, for the name they gave. A workflow with neither a registry entry nor a framework folder is fine: "add it to my AI Registry" becomes a follow-up action.

Read the full file on GitHub · 129 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

yesterday First seen · 129 lines · 187 tokens per session scan A 5de86a27d0e6

Subscribe to this mod's changes

writing-governance-records is a skill published in the GitHub repository jamesgray-ai/handsonai-plugins (8 stars, last pushed yesterday), licensed MIT. It adds 187 tokens to every session and 3,238 once invoked, about $0.0007 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 2026-11-06.

Building agents Writing and docs

writing-governance-records next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
writing-governance-recordsjamesgray-ai/handsonai-plugins	Skill	8	yesterday	MIT	A	187	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code