What is governance-setup?

A setup workflow for deciding how an AI assistant should be governed in a project.

Use it when first configuring governance or changing policies for coding assistants, data pipelines, or customer-facing bots.

It helps match approval rules, confidence requirements, drift monitoring, and post-task checks to the project’s risk level.

governance-setup — Skill for Claude Code by chrbailey

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 chrbailey/promptspeak-mcp-server --skill governance-setup

Clone the repo

git clone --depth 1 https://github.com/chrbailey/promptspeak-mcp-server

Made for: Claude Code.

Or install promptspeak, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

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/chrbailey/promptspeak-mcp-server/governance-setup/github.svg)](https://agentmods.dev/skills/chrbailey/promptspeak-mcp-server/governance-setup)

Your own site

<a href="https://agentmods.dev/skills/chrbailey/promptspeak-mcp-server/governance-setup"><img src="https://agentmods.dev/badge/skills/chrbailey/promptspeak-mcp-server/governance-setup/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/chrbailey/promptspeak-mcp-server/governance-setup"><img src="https://agentmods.dev/badge/skills/chrbailey/promptspeak-mcp-server/governance-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 480 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	$0.00032	$0.00480
Opus 5	$0.00016	$0.00240
Sonnet 5	$0.00006	$0.00096
Haiku 4.5	$0.00003	$0.00048

Measured 9d ago against content hash b4a685cc38ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

governance-setup 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 9d 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.

skills/governance-setup/SKILL.md · 38 lines

What it actually says

Governance Setup — PromptSpeak

You are helping the user configure PromptSpeak governance for their project.

Workflow

Assess the project context — Ask the user:
- What kind of agents will be governed? (coding assistants, data pipelines, customer-facing bots)
- What's the risk tolerance? (strict/regulated vs permissive/experimental)
- Are there specific tools or operations that must always require human approval?

Map answers to a governance profile, then let the user override specifics:

Profile	When to use	Confidence	Holds	Drift	Post-Audit
Lockdown	Regulated domains (legal, financial, healthcare), production with PII	0.95	All tool calls held for approval	ON, halt at 0.3	ON
Standard	Production coding assistants, internal tools, CI pipelines	0.7	Destructive ops only (deletes, deployments, external API writes)	ON, halt at 0.6	ON
Exploratory	Sandboxes, prototyping, hackathons, trusted single-user agents	0.3	None (log only)	OFF	OFF

Present all three profiles with the table above. Recommend Standard unless the user's answers clearly indicate otherwise. After the user picks a profile, ask: "Any overrides? For example, specific tools that should always require approval, or a different drift threshold."

Apply overrides on top of the chosen profile before proceeding to step 3.

Apply configuration using PromptSpeak tools:
- Set confidence thresholds with ps_confidence_bulk_set
- Configure hold behavior with ps_hold_config
- Set feature flags with ps_feature_set
- Register policy overlays with ps_config_set and ps_config_activate
Verify — Run ps_execute_dry_run with a sample frame to confirm the pipeline behaves as expected.
Export — Call ps_config_export so the user can save their configuration.

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.

9d ago First seen · 38 lines · 32 tokens per session scan A b4a685cc38ed

Subscribe to this mod's changes

governance-setup is a skill published in the GitHub repository chrbailey/promptspeak-mcp-server (1 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 480 once invoked, about $0.0002 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.

Building agents agent-governance ai-governance mcp mcp-server model-context-protocol pre-execution-blocking

memory-search-mcp

Long-term memory and context retrieval for AI agents. Semantic search across conversation history with care-weighted relevance.

CSOAI-ORG/memory-search-mcp · 0 tokens

web-research-mcp

Intelligent web research with source validation. Automated research synthesis with citation tracking and fact verification.

CSOAI-ORG/web-research-mcp · 0 tokens

api-canvas

DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…

cyanheads/secedgar-mcp-server · 85 tokens

governance-setup