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 PANGKAIFENG/ai-product-manager-skills --skill project-context-stewardgit clone --depth 1 https://github.com/PANGKAIFENG/ai-product-manager-skillsWrote 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/pangkaifeng/ai-product-manager-skills/project-context-steward)<a href="https://agentmods.dev/skills/pangkaifeng/ai-product-manager-skills/project-context-steward"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/project-context-steward/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/pangkaifeng/ai-product-manager-skills/project-context-steward"><img src="https://agentmods.dev/badge/skills/pangkaifeng/ai-product-manager-skills/project-context-steward.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00115 | $0.02178 |
| Opus 5 | $0.00057 | $0.01089 |
| Sonnet 5 | $0.00023 | $0.00436 |
| Haiku 4.5 | $0.00012 | $0.00218 |
Grade A, and why
project-context-steward 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 12d 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
项目上下文管家（project-context-steward）
中文速查
- 中文名：项目上下文管家 / 项目全局上下文维护
- 英文稳定名：
project-context-steward - 分类：项目治理
- 你可以这样叫我：
先完整看下项目并沉淀上下文、给这个项目建 PROJECT_CONTEXT.md、把这次踩坑更新到项目上下文 - 适合：进入新项目、跨仓库项目、长期需求协作前，扫描全局并生成或维护可复用项目上下文
- 不适合：单个 PRD 起草、纯目录治理、一次性 bug 修复、只需要代码 review 的任务
Overview
这个 Skill 用于把“新会话重新探索项目”的成本降下来。它帮助 Codex 先建立项目级事实、边界、入口路由和维护规则，再把长期有效的信息沉淀到 PROJECT_CONTEXT.md 或等价项目上下文文档。
核心原则：项目上下文文档不是某个需求的 PRD。它只记录跨需求复用的全局知识；阶段性判断、具体版本方案和待确认问题应进入 prd/、research/、discussions/ 或 decisions/。
Trigger Boundary
Use this Skill when the user asks to:
- onboard into a new repository or multi-repo workspace;
- generate a durable
PROJECT_CONTEXT.md,CONTEXT.md, project map, or first-read document; - update project context after a requirement, architecture change, or repeated pitfall;
- decide what belongs in global context versus PRD, ADR, research, handoff, runbook, or directory rules.
Do not use this Skill when:
- the user only wants a specific PRD: use
prd-architect; - the user only wants PRD critique: use
prd-review; - the user only asks where files should go: use
project-structure-governor; - the user asks to migrate a messy legacy directory: use
legacy-project-structure-migrator; - the user asks for a one-off implementation: inspect the relevant repo and implement normally.
Workflow
0. Intake Required Context
Before scanning, capture the minimum inputs that change the result:
- target project root or workspace path;
- desired context document path, if the user already has one;
- whether the user wants create, refactor, or incremental maintenance;
- known sibling repositories that must not be confused;
- any user-stated product facts, decisions, or pitfalls from the current conversation.
If a required input is discoverable from the local workspace, discover it instead of asking. If a missing input changes where files will be written, ask a short clarification before editing.
1. Scope The Project
Identify the actual project boundary before writing anything.
What ships with it
7 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.
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.
- 12d ago First seen · 241 lines · 115 tokens per session scan A 9d3683d0e199
project-context-steward is a skill published in the GitHub repository PANGKAIFENG/ai-product-manager-skills (11 stars, last pushed 13d ago), licensed MIT. It adds 115 tokens to every session and 2,178 once invoked, about $0.0006 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
agent-wiki
Incremental LLM-friendly wiki generator for Obsidian note vaults. Use when: (1) Building wiki from notes, (2) Ingesting notes to wiki, (3) Obsidian LLM wiki, (4) Incremental knowledge base management. Triggers: 'build wiki from notes', 'ingest notes to wiki', 'Obsidian LLM wiki', 'incremental knowledge base'.
capability-evolver
Self-evolution workflow for the agent. Before substantive work, recall past outcomes from evolution memory; while editing, detect improvement signals; at task end, record the outcome; when reusable, distill or search the EvoMap network for proven genes/capsules. Use when the user starts non-trivial work (a feature, a…
grill-me
Grill the user about a requirement, decision, or idea before implementation, then produce an actionable planning report without writing code. Use when the user wants to clarify requirements, stress-test an idea, compare approaches, or plan before coding.
context-optimizer
A context-management assistant for long conversations with AI agents. It helps organize the information an agent needs when conversations become large or contain conflicting details.
eol-process
Run a product sunset end to end — decide, align, plan, prepare, announce, close. Use when you need the whole EOL process, not just one artifact.
epic-breakdown-advisor
Break down epics into user stories with Humanizing Work split patterns. Use when a backlog item is too large to estimate, sequence, or deliver safely.