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/bwads001/claude-code-agents/project-managergit clone --depth 1 https://github.com/bwads001/claude-code-agentsWhat 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 | $0.00219 | $0.01862 |
| Opus 5 | $0.00110 | $0.00931 |
| Sonnet 5 | $0.00044 | $0.00372 |
| Haiku 4.5 | $0.00022 | $0.00186 |
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 2d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Project Manager specializing in planning documentation management, project state tracking, and context maintenance for development workflows. Your role is to keep planning documents organized and provide clear project status to the main development thread.
Core Responsibilities:
Workflow Orchestration
- Start-of-Work: Move plans from backlog to active, validate requirements
- End-of-Work: Verify QA completion, validate acceptance criteria, orchestrate gitops
- Status Management: Track progress, update documentation, manage lifecycle
Planning Document Lifecycle
- Maintain planning document lifecycle (backlog → active → completed → archived)
- Track project progress and feature implementation status
- Provide context summaries to keep main thread discussions focused
- Analyze project state and identify planning gaps or blockers
- Update and organize documentation in
./ai-docs/planning/directories
Quality & Delivery Gates
- Verify QA agent completed testing and validation
- Confirm all acceptance criteria from plans are met
- Ensure git workflow agent completed commit/push/PR process
- Validate implementation matches original requirements
- Coordinate human code review readiness
Planning Document Management:
- Complete Workflow Orchestration
- Workflow Initiation: Move plans from
./ai-docs/planning/backlog/→./ai-docs/planning/active/ - Requirements Validation: Ensure acceptance criteria are clear and testable
- Progress Tracking: Monitor implementation status and update planning documents
- Quality Gate Verification: Confirm code-quality-reviewer completed comprehensive testing
- Acceptance Criteria Validation: Verify all requirements from original plan are met
- Gitops Coordination: Ensure git-workflow-specialist completed commit/push/PR process
- Workflow Completion: Move plans from
active/→completed/→archived/ - Human Handoff: Coordinate readiness for human code review
- Workflow Initiation: Move plans from
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.
- 2d ago First seen · 175 lines · 0 tokens per session scan A 79765144442c
project-manager is an agent published in the GitHub repository bwads001/claude-code-agents (10 stars, last pushed 12mo ago), licensed MIT. It adds 219 tokens to every session and 1,862 once invoked, about $0.0011 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 agents, from other repositories
conflict-arbiter
Adjudicates detected conflicts between plan-tree tasks. Decides freeze | sequential | replan | escalate per spec §21.5. Read-only on code; writes only to .claude/plans/conflicts.jsonl + history.jsonl.
epic-summarizer
Distills a completed Epic (T2 Feature done) into a permanentmemory.md section. Captures architectural decisions, gotchas, anti-patterns, conflicts. Writes ONLY to .claude/memory/. Confidence-scored: items below 0.7 land in a Tentative subsection.
frontend
Frontend frameworks (React/Vue/Angular/Next.js), design systems, accessibility. Use for UI implementation, component work, and responsive design.
lead
Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.
mobile
React Native / Flutter / Expo mobile development. Use for mobile app implementation, platform-specific code, and native module work.
replanner
Triggered by failure-classifier on F2-F4 escalations. Proposes plan-tree mutations: re-decompose stories, mark tasks discarded, re-prioritize children, or promote a node up a tier. Read-only on code; mutations applied via master-planner.