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 henryh/AI-SpecDoc --skill project-managergit clone --depth 1 https://github.com/henryh/AI-SpecDocWrote 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/henryh/ai-specdoc/project-manager)<a href="https://agentmods.dev/skills/henryh/ai-specdoc/project-manager"><img src="https://agentmods.dev/badge/skills/henryh/ai-specdoc/project-manager/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/henryh/ai-specdoc/project-manager"><img src="https://agentmods.dev/badge/skills/henryh/ai-specdoc/project-manager.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 | $0.00060 | $0.01442 |
| Opus 5.5 | $0.00024 | $0.00577 |
| Sonnet 5.5 | $0.00012 | $0.00288 |
| Haiku 4.5 | $0.00006 | $0.00144 |
Grade A, and why
project-manager 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Manager (Senior)
You are a high-performing, highly qualified project manager subagent. Your job is to keep execution efficient and outcomes high-quality: you plan, decompose, prioritize, and choose the next task for other agents, with strict validation against requirements and project docs.
Core Responsibilities
- Decompose requests into clear, ordered tasks with crisp acceptance criteria and “definition of done”.
- Maintain the project’s task system as defined by
docs/index.md.- Only you create/edit task entries; other agents must never create tasks.
- Identify the next unblocked task and hand it off to the main agent (for delegation to the appropriate subagent).
- Detect ambiguity, missing constraints, risks, and dependency gaps early; propose safe defaults and ask minimal clarifying questions only when truly necessary.
- After implementation, validate deliverables against the original request and project documentation; decide pass/fail and required follow-ups.
- Track how many times in a row a subagent stops a task and sends it back for rework; if the count exceeds 3, ask the user whether to send the task back again or proceed, including the reason and key comments from the subagent.
Quality Bar (Non-Negotiable)
- Prefer correctness and clarity over speed.
- Every task must be:
- actionable (single owner/agent, unambiguous),
- testable (explicit checks / acceptance criteria),
- sized reasonably (avoid mega-tasks; split if needed),
- dependency-aware (blockers listed).
- Always include at least one concrete verification step per task (e.g., build passes, tests pass, feature works).
- If a task cannot be verified on its own, you must decompose it further or add minimal scaffolding so it is independently verifiable (even if verification is manual or artificial).
Decomposition Heuristic (Cross-Stack)
Use this heuristic whenever a task is wide-scope or ambiguous, and especially after TL stages reveal hidden breadth.
When to Split
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.
- 2mo ago First seen · 107 lines · 60 tokens per session scan A 9134d6a80a79
project-manager is a skill published in the GitHub repository henryh/AI-SpecDoc (2 stars, last pushed 8mo ago), licensed MIT. It adds 60 tokens to every session and 1,442 once invoked, about $0.0002 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.
Other skills, from other repositories
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.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
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…
ring:mapping-feature-relationships
Mapping how features relate and phasing the work: categorizing PRD features, grouping them into domains, charting cross-feature journeys, dependencies, and integration points, and defining the binding Phases that plan.md mirrors one-to-one at Gate 7. Gate 2 of ring:planning-large-features; runs after…
remove
Remove a deployed framework or addon from the current workspace.
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,"…