A project-management skill that registers and manages local code repositories through `repos.json`, a file listing projects and their locations. It can also record whether a project is public or private and which language to use for interactions.

Adding or removing projects, locating a registered project, discovering its Git details and applying project-specific language preferences.

It gives the assistant a reliable way to find registered projects and their local folders, including a specific folder inside a larger repository. This avoids repeatedly supplying project paths and settings.

How ZhuoZhuoCrayon/ai-workspace configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to ZhuoZhuoCrayon/ai-workspace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ZhuoZhuoCrayon/ai-workspace/main/.agents/skills/project-mgr/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/ZhuoZhuoCrayon/ai-workspace

Made for: Claude Code, 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/zhuozhuocrayon/ai-workspace/project-mgr/github.svg)](https://agentmods.dev/skills/zhuozhuocrayon/ai-workspace/project-mgr)

Your own site

<a href="https://agentmods.dev/skills/zhuozhuocrayon/ai-workspace/project-mgr"><img src="https://agentmods.dev/badge/skills/zhuozhuocrayon/ai-workspace/project-mgr/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/zhuozhuocrayon/ai-workspace/project-mgr"><img src="https://agentmods.dev/badge/skills/zhuozhuocrayon/ai-workspace/project-mgr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,129 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	$0.00089	$0.02129
Opus 5.5	$0.00036	$0.00852
Sonnet 5.5	$0.00018	$0.00426
Haiku 4.5	$0.00009	$0.00213

Measured 13d ago against content hash 4ff4426c57c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

project-mgr 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 13d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/list_skills.py, scripts/registry.py, tests/test_list_skills.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.

.agents/skills/project-mgr/SKILL.md · 185 lines

How it starts

The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.

project-mgr — 项目管理

管理工作区中项目的添加、删除和定位，默认 visibility 为 public。

项目通过 repos.json / private/repos.json 注册。私有项目的键为 private/<name>。

local_path 是相对路径。直接读注册表时，全路径按这个规则拼：

根目录 = PROJECTS_ROOT 或 repos.local.json 的 projects_root，都没有时用 ~/Project
克隆目录 = 根目录 / local_path
项目目录 = 克隆目录 / subdir

subdir 缺省是 .。repos.local.json 的 projects.<key> 直接给克隆目录，不再拼接。self 条目的项目目录是工作区根目录。

定位时优先执行：

python3 .agents/skills/project-mgr/scripts/registry.py path <key>

0x01 添加项目

a. 输入参数

参数	必填	说明
local_path	是	本地路径（仓库根目录或大仓子目录均可）
visibility	否	public（默认） / private
name	否	项目名称覆盖（默认从 `local_path` 的 basename 推断）
language	否	项目语言偏好：`zh`（默认） / `en`，影响 PR review 评论、commit message 等交互语言
user_name	否	仅 private。仓库本地 Git `user.name`，与 `user_email` 成对填写或成对省略
user_email	否	仅 private。仓库本地 Git `user.email`，与 `user_name` 成对填写或成对省略

b. 自动发现

先 cd 到 local_path，再逐条执行以下 Git 命令采集信息（Git 在子目录中会自动向上查找 .git）：

信息	命令	说明
远程仓库地址	`git remote -v`	优先取 `upstream`（fetch），其次 `origin`（fetch）
默认分支	`git symbolic-ref refs/remotes/<remote>/HEAD 2>/dev/null`	失败则回退检测 `master` / `main` 分支是否存在
仓库描述	`gh repo view <owner>/<repo> --json description -q .description`（可用时）	GH 描述优先，不可用时回退本地 `README.md` 首段摘要

推断规则：

local_path：直接使用用户提供的路径，不回退到仓库根目录（大仓场景下用户只关心子目录）
项目名称：取 local_path 的 basename（如 /path/bk-monitor/bkmonitor → bkmonitor），用户可通过 name 参数覆盖
远程仓库地址：含 token 或凭据时先剔除凭据，统一格式化为 https://github.com/<owner>/<repo>.git 记录
仓库描述（description）补齐策略（不能为空）：
1. 优先使用 Git 平台描述（GitHub/GHE，gh repo view 或 API）。
2. 若平台不可达或描述为空，回退读取 <local_path>/README.md：取首个 # 标题后第一段非空正文作为摘要。
3. 若仍为空，使用简短占位描述：<name> 项目仓库，并在回复中标注“建议后续人工完善”。

Read the full file on GitHub · 185 lines

Files

What ships with it

4 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.

13d ago Changed · +14 lines 4ff4426c57c4
14d ago Changed · +17 lines · +33 tokens per session a5d56fe27488
18d ago Changed · +2 lines e975f231cdda
2mo ago First seen · 152 lines · 56 tokens per session scan A 9d1ebbb8c3c2

Subscribe to this mod's changes

project-mgr is a skill published in the GitHub repository ZhuoZhuoCrayon/ai-workspace (27 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 2,129 once invoked, about $0.0004 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 2026-08-30.

Project management

story-readiness

Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.

Donchitos/Claude-Code-Game-Studios · 48 tokens

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

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…

specstoryai/getspecstory · 126 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

qa-project-bootstrap

Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…

petrkindlmann/qa-skills · 124 tokens

remove

Remove a deployed framework or addon from the current workspace.

jmagly/aiwg · 12 tokens

ai-workspace: Skill for Claude Code