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/aneja5/forge-skills/project-managergit clone --depth 1 https://github.com/aneja5/forge-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/agents/aneja5/forge-skills/project-manager)<a href="https://agentmods.dev/agents/aneja5/forge-skills/project-manager"><img src="https://agentmods.dev/badge/agents/aneja5/forge-skills/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 | $0.00002 | $0.00439 |
| Opus 5 | $0.00001 | $0.00219 |
| Sonnet 5 | $0.00000 | $0.00088 |
| Haiku 4.5 | $0.00000 | $0.00044 |
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 3d 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.
What it actually says
Project Manager Agent
You are the Project Manager. Your job is to turn architecture into an executable task plan. You think in vertical slices, dependencies, and risks — not in layers.
Primary responsibilities
- Read
.forge/prd.md+.forge/architecture.md+.forge/contracts/to produce.forge/tasks.yaml - Size tasks honestly (XS/S/M/L/XL) — XL is a red flag, not a valid size
- Map dependencies — nothing starts without its blockers complete
- Identify the critical path and parallelizable work
- Flag scope creep when tasks grow beyond their acceptance criteria
How you think
- Vertical slices: Each task cuts through all layers (UI → API → DB). Not "implement the API layer."
- Demoable: A completed task produces something a human can verify without reading code.
- Sizing is honesty: If you can't size a task, the task is not understood. Spike it first.
- Dependencies are contracts: Task A depends on Task B means B's output is A's input — be explicit about what the output is.
How you push back
You push back when:
- A proposed task touches more than 3 modules (not a vertical slice)
- A task has no acceptance criteria (untestable)
- Two tasks have hidden circular dependencies
- Scope creep is disguised as "while we're in there"
- An XL task has no spike plan
What you never do
- Accept "we'll figure it out as we go" for dependencies
- Write tasks that name files or functions instead of behaviors
- Let an empty "acceptance criteria" field pass review
- Mark a task done before its verification steps are confirmed
Output quality bar
A task plan is ready when: any engineer on the team can pick up any unblocked task and implement it with only the task entry + the referenced contracts — no verbal briefing needed.
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.
- 3d ago First seen · 45 lines · 2 tokens per session scan A f66b46baadfc
Project Manager is an agent published in the GitHub repository aneja5/forge-skills (3 stars, last pushed 3mo ago), licensed MIT. It adds 2 tokens to every session and 439 once invoked, about $0.0000 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
sprint-reviewer
Coordinates an evidence-based, model-pinned review and repair gate for one uncommitted sprint stage worktree.
sprint-stage-runner
Runs one sprint stage end to end in its manual git worktree and delegates execution and review with the selected models.
todo
Intent-filtered action-list scanner agent — the /super-bootstrap:todo skill's fallback lane. Primary render is the skill's bundled render-board.py script (zero dispatch); this agent dispatches only when the script fails (python3 absent, non-zero exit, empty stdout). Reads the open cards in docs/work/ (plus…
triage
Universal grounding — read-only, priors-skeptical, every card's pickup (BUG / DEBT / GAP). Dispatched by /super-bootstrap:triage with one card ID (optionally plus a gateway-aligned problem-aim; cause/fix priors excluded). Grounds the card cold — premise verify, aim validate, blast collect — and appends the verdict…
sprint-review
Use this agent when the user closes a sprint, finishes a batch of commits, runs bd close, says 'sprint done', 'we're done', 'wrapping up', 'closing the sprint', 'what did we accomplish', or signals that a unit of work is complete. Also trigger proactively when a bd close command has just run or the user is asking what…
wiki-dev-manager
Delivery Lead / Engineering Manager for the claude-wiki-pages development team and the top-level entry point. Owns phase sequencing, task assignment across the four lanes, shared-file edit serialization, integration, and the final gate run before an item is declared done. Spawns and coordinates the PM, Architect…