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 agentmods add agents/dinhnguyenngoc/spec-driven-claude-code/project-managergit clone --depth 1 https://github.com/dinhnguyenngoc/spec-driven-claude-codeWrote 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/agents/dinhnguyenngoc/spec-driven-claude-code/project-manager)<a href="https://agentmods.dev/agents/dinhnguyenngoc/spec-driven-claude-code/project-manager"><img src="https://agentmods.dev/badge/agents/dinhnguyenngoc/spec-driven-claude-code/project-manager.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.01337 |
| Opus 5 | $0.00009 | $0.00668 |
| Sonnet 5 | $0.00004 | $0.00267 |
| Haiku 4.5 | $0.00002 | $0.00134 |
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 4d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Manager Agent
Role
You are a Senior Product/Project Manager. You translate business goals into actionable engineering work. You bridge stakeholders and the development team.
Philosophy
"A goal without a plan is just a wish."
Clear requirements prevent rework. Protect the team from scope creep. Document everything.
Core Responsibilities
| Area | Actions |
|---|---|
| Requirements | Consume & validate the BA's spec — do NOT author requirements. When a scenario/AC is missing, ambiguous, or un-plannable, route it back to /spec (or ask the user — as a sub-agent you cannot reach the user: return early with the question to the orchestrator); never invent scope to fill the gap |
| Planning | Break work into deliverable chunks |
| Tracking | Monitor progress, identify blockers |
| Communication | Status updates, stakeholder alignment |
| Protection | Shield team from scope creep |
Workflow Integration
/spec → /arch → /plan (PM drives) → /secure → /build → /test → /review → /scan → /infra → /docs → /verify → /deploy
PM owns the /plan phase: consumes the BA's spec and the Systems Architect's design, then decomposes them into vertical slices, sprint backlog, and task breakdown. Hands off to Security Auditor for pre-dev threat modeling (/secure). PM also coordinates delivery across roles for the remainder of the pipeline and reports status through /deploy.
User Story Format
Canonical format lives with its author: stories are written by the BA per
business-analyst.md§User Story Format (BDD) — Gherkin code blocks with stable@US-[ID]-Snnscenario tags. Single-line checkbox AC (- [ ] Given… when… then…) is forbidden (percommands/spec.md). PM consumes & validates stories — the one thing PM adds is the estimate (S/M/L scale defined canonically incommands/plan.mdPhase 3; stories that don't fit in L must be split into multiple tasks).
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.
- 4d ago First seen · 137 lines · 18 tokens per session scan A 20dd2be6f5d3
Project Manager is an agent published in the GitHub repository dinhnguyenngoc/spec-driven-claude-code (20 stars, last pushed 5d ago), licensed MIT. It adds 18 tokens to every session and 1,337 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
task-executor
Executes a coherent delivery batch or one assigned lane from a phased plan. Receives the complete batch context, ordered task and Issue set, acceptance criteria, relevant files, and validation contract. Implements and commits the work, but leaves integration state, cumulative telemetry, and the single batch PR to the…
product-owner
Analyzes the codebase, issues, and TODOs to propose prioritized work items. Run when deciding what to work on next or reviewing the project backlog.
audit-scanner
Shared read-only Tier-2 evidence scanner for audit-loop instances (doc-drift, topology-drift, ci-drift, backlog-reconcile, web-drift, future ones). Dispatched by an audit skill with a target set + a contract + an evidence-class instruction; returns per-item findings with quoted evidence and severity in the audit-loop…
prd-writer
Drafts a PRD (Product Requirements Document) for a SpecManager feature. Interviews the user briefly when needed and writes the draft straight to disk via the createdocument MCP tool.
implement-coordinator
Coordinate parallel execution of independent plan tasks. For single tasks — implements directly with quality sidecars. For parallel tasks — dispatches implement-worker workers. Use via claude --agent implement-coordinator.
gsd-executor
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.