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.
npx skills add 1972143344-max/project-governance-skill --skill project-governancegit clone --depth 1 https://github.com/1972143344-max/project-governance-skillWrote 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.
[](https://agentmods.dev/skills/1972143344-max/project-governance-skill/project-governance)<a href="https://agentmods.dev/skills/1972143344-max/project-governance-skill/project-governance"><img src="https://agentmods.dev/badge/skills/1972143344-max/project-governance-skill/project-governance/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.
<a href="https://agentmods.dev/skills/1972143344-max/project-governance-skill/project-governance"><img src="https://agentmods.dev/badge/skills/1972143344-max/project-governance-skill/project-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00063 | $0.03024 |
| Opus 5 | $0.00032 | $0.01512 |
| Sonnet 5 | $0.00013 | $0.00605 |
| Haiku 4.5 | $0.00006 | $0.00302 |
Grade A, and why
project-governance 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Governance
Use this skill to operate a project-scoped governance system without letting the skill itself become repository truth.
Default to docs/<project-scope>/governance/ with sibling context/ and tasks/ directories under the same docs/<project-scope>/ scope. Use repository-wide docs/governance/ only when the user explicitly wants one governance layer shared across multiple projects or experiments.
G0. Front Door
Use This Skill When
- the user asks to initialize, adopt, re-enter, or maintain governance docs
- the repo has stale notes, conflicting design records, or unclear authority order
- the task needs spec/design/decision/task-record governance before non-trivial changes
- structural document maintenance could change what future agents read first
- recovery or context state may matter after compression, handoff, or pause
Do Not Use This Skill When
- the task is a small code or docs change with no governance-sensitive surface
- the work only needs ordinary repo reading and does not involve governance maintenance
- the user wants implementation only and no governance workflow is active
Skill Boundary And Precedence
This skill is a workflow surface, not a repository-truth source.
Treat these layers as distinct:
- repository docs answer what is true here now
- applicable
AGENTS.mdfiles answer what durable collaboration rules remain active here - this skill answers how to operate the governance workflow
Precedence remains:
- direct user instruction
- written repository authority docs
- applicable
AGENTS.md - this skill
Do not let the skill silently absorb repository authority.
Re-entry Trigger
Re-open this main SKILL.md when:
- governance initialization or adoption is about to happen
- structural maintenance may change future reading behavior
- context was compressed, summarized, or handed off
- written repo docs,
AGENTS.md, and remembered workflow may have drifted apart - conclusions may need promotion from recovery or execution into authority or learning
What ships with it
36 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.
- 10_runtime_reading_protocol.md 5.2 KB
- 11_governance_execution_contract.md 4.8 KB
- agents/openai.yaml 401 B
- assets/00_context_index.template.md 2.4 KB
- assets/00_index_and_priority.template.md 13 KB
- assets/00_project_scope_registry.template.md 2.1 KB
- assets/00_task_knowledge_base.template.md 1.7 KB
- assets/01_constraints_and_spec.template.md 1.3 KB
- assets/01_context_usage_and_policy.template.md 5.8 KB
- assets/02_design.template.md 1.2 KB
- assets/03_behavior_audit.template.md 2.3 KB
- assets/04_lessons_learned.template.md 2.6 KB
- assets/05_decision_log.template.md 1.6 KB
- assets/06_active_plan.template.md 2.1 KB
- assets/07_governance_behavior_matrix.template.md 9.7 KB
- assets/08_probe_harness_contract.template.md 3.8 KB
- assets/09_governance_system_spec.template.md 5.5 KB
- assets/10_runtime_reading_protocol.template.md 6.1 KB
- assets/11_governance_execution_contract.template.md 3.7 KB
- assets/context-shard.template.md 1.6 KB
- assets/file-summary-header.template.md 711 B
- assets/lessons/LES.template.md 1.3 KB
- assets/project-root-AGENTS.template.md 6.0 KB
- assets/summary-index.template.md 2.4 KB
- assets/tasks/templates/00_task_template_index.template.md 3.4 KB
- assets/tasks/templates/T0-minor.template.md 515 B
- assets/tasks/templates/T1-probe-review-docs.template.md 2.0 KB
- assets/tasks/templates/T2-implementation.template.md 1001 B
- assets/tasks/templates/T3-substantial-change.template.md 1.2 KB
- governance-surface-catalog.md 2.6 KB
- index-summary-reference.md 2.1 KB
- initialization-and-adoption.md 3.2 KB
- lane-reference.md 3.7 KB
- recovery-method-reference.md 1.6 KB
- references/acceptance-scenarios.md 14 KB
- references/governance-workflow.md 16 KB
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.
- 11d ago First seen · 404 lines · 63 tokens per session scan A 603d70668f85
project-governance is a skill published in the GitHub repository 1972143344-max/project-governance-skill (2 stars, last pushed 4mo ago), licensed MIT. It adds 63 tokens to every session and 3,024 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.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.