What is senmu-build-project?

A project-governance skill for deciding who owns important project information, how the project is structured, and how work moves between stages. It covers both starting a project and repairing governance in an existing one.

Use it to plan a new project's governance, assess or reorganize a mature project, map its folders and documentation owners, or establish an owner for work that spans multiple stages.

It helps resolve unclear ownership, conflicting authorities, missing project structure, and unreliable sources of status information.

senmu-build-project — Skill for Claude Code and Codex by SenMuShare

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 SenMuShare/senmu-buildos --skill senmu-build-project

Clone the repo

git clone --depth 1 https://github.com/SenMuShare/senmu-buildos

Made for: Claude Code, Codex.

Or install senmu-buildos, the plugin that ships this one along with the rest of its 9 skills, 2 hooks.

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/senmushare/senmu-buildos/senmu-build-project/github.svg)](https://agentmods.dev/skills/senmushare/senmu-buildos/senmu-build-project)

Your own site

<a href="https://agentmods.dev/skills/senmushare/senmu-buildos/senmu-build-project"><img src="https://agentmods.dev/badge/skills/senmushare/senmu-buildos/senmu-build-project/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/senmushare/senmu-buildos/senmu-build-project"><img src="https://agentmods.dev/badge/skills/senmushare/senmu-buildos/senmu-build-project.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 615 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	$0.00615
Opus 5	$0.00016	$0.00308
Sonnet 5	$0.00006	$0.00123
Haiku 4.5	$0.00003	$0.00061

Measured 3d ago against content hash 43bcdf5e2cd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

senmu-build-project 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 3d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/assess_project_governance.py, scripts/init_project_governance.py, scripts/validate_mature_project_governance.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/senmu-build-project/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Governance

Own the governance instance, authority structure, and cross-domain ownership boundaries; this is not a parent skill. Return ordinary work when project entrypoints suffice. Continue only for missing/conflicting governance, structural evolution, state-owner repair, or explicit governance work.

Route by Outcome

Create, assess, evolve governance: Governance Instances.
Staged established-project takeover: Project Takeover.
Lifecycle, capability composition, done: Project Practice.
Roots, layout, document ownership, maps: Directories.
Discover/maintain effective AGENTS and on-demand standards: Standards Discovery.
Create/select/repair cross-stage task state: Task State.
Project situations, handoffs, skill boundaries: Adoption and Routing.
Read Governance Levels only for an actual G0-G4/gate decision.

Read only what the outcome needs. Delivery owns Git execution.

Use init_project_governance.py for new projects and assess_project_governance.py for zero-write established-project inventory. Default to bounded output; use --verbose only for complete registers. Script output is candidate fact, not confirmation, authorization, or runtime proof.

Core Contract

Establish authoritative root, Git/subproject/release-unit boundaries, entrypoints, owners, authorization, and non-goals. User intent/authority outranks Skill defaults; host permissions apply.
For one placement question, give the preferred owner/path and reason; do not write unless requested.
Run init_project_governance.py --mode plan-new before explicitly authorized initialize-new.
Inventory established projects read-only, then confirm owners semantically. Never overwrite them with defaults or create parallel truth.
Shape structure around actual capabilities, lifecycle, and release units; project types do not replace facts or justify speculative modules.
Maps navigate owners, entrypoints, state, and boundaries. Root AGENTS.md holds project differences, real commands, and overrides only.
Use one Durable Task State Owner across stages. Continuing an existing task does not reactivate Project.
Authorize initialization, migration, and remediation separately. Plans, script output, and static checks are not execution facts.

Read the full file on GitHub · 37 lines

Files

What ships with it

24 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.

3d ago Changed 43bcdf5e2cd4
5d ago Changed d79c2595f853
7d ago Changed 3c1d8fdfbd6b
8d ago Changed · -25 tokens per session 4c668a46cfd7
12d ago First seen · 37 lines · 57 tokens per session scan A f2aa4c4049ba

Subscribe to this mod's changes

senmu-build-project is a skill published in the GitHub repository SenMuShare/senmu-buildos (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 32 tokens to every session and 615 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.

Planning Project Management Project management ai-agents codex codex-plugin openai-codex project-governance

openproject-codex

Use the OpenProject Codex plugin to inspect and manage work in Codex through the OpenProject API.

varaprasadreddy9676/openproject-codex-plugin · 27 tokens

github-project-management

Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning.

ruvnet/RuView · 25 tokens

manage-taskboard

Manage Codex Taskboard / e-taskboard work with taskctl. Use for taskboard issue IDs, status sync, comments, or taskctl cloud setup—not for unrelated product docs.

chuspeeism/dashi-taskboard · 41 tokens

decision-map

Turn a loose idea into a git-tracked, session-resumable map of typed investigation tickets, then drive them to resolution one at a time. The planning-loop engine for work that is still being figured out — too fuzzy for a campaign, too big for a single intake item. Resolved tickets graduate into .planning/intake/ for…

SethGammon/Citadel · 77 tokens

meegle

A guide and command-line interface for managing Feishu/Lark Meego project data, including work items, workflow steps, views, personal tasks, and schedules. Feishu/Lark is a collaboration platform, while Meego is its project-management system.

larksuite/meegle-cli · 126 tokens

ambient-project

Quietly maintain a useful project view from meaningful work in the current Codex session. Use when work creates a task, bug, decision, idea, risk, milestone, plan, progress update, or explicit completion.

Bene-2020/plane-codex-mcp · 46 tokens