project-structure-governance

project-structure-governance is a skill for Codex from ashermahonin/agentic-skills. It costs 72 tokens per session (952 once invoked), scanned A, original, MIT.

A repository-organization method for keeping source code, tests, scripts, documentation, generated files, and temporary work understandable.

In plain words
What is it for?
Mapping the project, checking existing conventions, choosing locations for temporary files, cleaning up scratch artifacts, and maintaining a clear documentation entry point.
Why use it?
It prevents agent-created clutter, duplicate instructions, misplaced artifacts, and unclear documentation after development work is complete.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

Good fit Mapping the project, checking existing conventions, choosing locations for temporary files, cleaning up scratch artifacts, and maintaining a clear documentation entry point.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ashermahonin/agentic-skills/project-structure-governance
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 ashermahonin/agentic-skills --skill project-structure-governance
Clone the repo
git clone --depth 1 https://github.com/ashermahonin/agentic-skills

Made for: 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 project-structure-governance

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

agentmods 80×15 button for project-structure-governance

Your own site · 80×15
<a href="https://agentmods.dev/skills/ashermahonin/agentic-skills/project-structure-governance"><img src="https://agentmods.dev/badge/skills/ashermahonin/agentic-skills/project-structure-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 952 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 $0.00072 $0.00952
Opus 5.5 $0.00029 $0.00381
Sonnet 5.5 $0.00014 $0.00190
Haiku 4.5 $0.00007 $0.00095

Measured 2mo ago against content hash b28db9a72269, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

project-structure-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 2mo 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.

agentic/skills/project-structure-governance/SKILL.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Structure Governance

Purpose

Keep the repository understandable after the agent leaves. Treat structure, temporary artifacts, test scripts, and documentation entrypoints as part of the deliverable, not as cleanup someone else will do later.

Repository state

  1. Read references/project-activity-contract.md.
  2. Identify the project type, existing conventions, and current documentation entrypoint (README.md, docs/README.md, RUNBOOK.md, AGENTS.md, CLAUDE.md, or equivalent).
  3. Inspect the repo root and common scratch locations for clutter: one-off scripts, generated outputs, screenshots, temp logs, duplicate instructions, abandoned migration helpers, and stale test harnesses.
  4. Confirm where temporary/test artifacts should live for this repo. Prefer an existing convention; otherwise use a dedicated ignored workspace such as .agent-work/, .tmp/agent/, or tools/agent/ depending on project norms.
  5. Record any required cleanup, consolidation, or documentation-entrypoint work before implementation expands the file surface.

Structure rules

  1. Structure contract. Define or verify the top-level repo map: source, tests, tools, docs, scripts, infra, assets, fixtures, generated artifacts, and agent-only workspace.
  2. Artifact routing. Route every new file before creating it: production source, test fixture, reusable tool, temporary experiment, generated output, documentation, or project memory.
  3. Temporary isolation. Put throwaway scripts, debug probes, generated logs, screenshots, benchmark scratch, and exploratory outputs in the dedicated agent/test workspace. Do not place them in repo root.
  4. Reusable promotion. Promote a temporary script only if it has a stable name, documented purpose, safe flags, validation command, owner, and a permanent home such as tools/, scripts/, tests/fixtures/, or docs/examples/.
  5. Documentation entrypoint. Maintain one canonical entrypoint that links outward: README for project overview, docs/README.md for deep docs when needed, and one runbook/index for operation. Avoid multiple competing “START_HERE”, “HOW_TO”, “FINAL”, “NEW_README”, or duplicate setup files.
  6. Runbook hygiene. If operational commands, install steps, local dev setup, release, rollback, or incident response changed, update the canonical runbook/index instead of adding a standalone note.
  7. Root cleanliness check. Before handoff, verify the repo root contains only intentional files. Move, delete, or document anything temporary according to the contract.
  8. Graph update. Hand documentation changes to documentation-graph-curator so Obsidian memory points to the canonical entrypoint and does not preserve obsolete instructions as current truth.

Read the full file on GitHub · 62 lines

Files

What ships with it

2 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.

  1. 2mo ago First seen · 62 lines · 72 tokens per session scan A b28db9a72269

Subscribe to this mod's changes

project-structure-governance is a skill published in the GitHub repository ashermahonin/agentic-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 72 tokens to every session and 952 once invoked, about $0.0003 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.

Related

project-structure-governance compared with skills from other repositories

project-structure-governance next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
project-structure-governanceashermahonin/agentic-skillsSkill102mo agoMITA72Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code