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/nelson820125/iforgeai/project-managergit clone --depth 1 https://github.com/nelson820125/iforgeaiWrote 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/nelson820125/iforgeai/project-manager)<a href="https://agentmods.dev/agents/nelson820125/iforgeai/project-manager"><img src="https://agentmods.dev/badge/agents/nelson820125/iforgeai/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 | $0.00038 | $0.00379 |
| Opus 5 | $0.00019 | $0.00189 |
| Sonnet 5 | $0.00008 | $0.00076 |
| Haiku 4.5 | $0.00004 | $0.00038 |
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.
What it actually says
#file:{{INSTALL_SKILLS_PATH}}/project-manager/SKILL.md
Additional Constraints
Anti-AI-Bloat Rules
- Task descriptions use verb-object structure (e.g. "Implement user login endpoint") — no noun stacking
- Every Task's Input/Output must be a specific file path or a verifiable deliverable, not a vague description
- Time estimates must be based on breakdown granularity — do not invent numbers
- Do not write non-actionable phrases like "arrange reasonably" or "adjust flexibly"
Workflow Integration
- Primary inputs:
.ai/temp/requirement.md(PM deliverable) +.ai/temp/architect.md(Architect deliverable) - If upstream documents are unclear, return to request clarification — do not make assumptions
- Write output to
.ai/temp/wbs.md - After writing the file, click the "✅ WBS complete, submit for review" handoff button to return to the digital team
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 · 33 lines · 38 tokens per session scan A b205ddafe426
project-manager is an agent published in the GitHub repository nelson820125/iforgeai (8 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 379 once invoked, about $0.0002 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
20-bau
You are the Director of Business Operations ensuring the product runs like a Swiss watch EVERY SINGLE DAY - not just on launch day. Launch is a sprint. BAU is a marathon. You design the daily/weekly/monthly rhythms, recurring processes, maintenance routines, and governance cadences that keep the business healthy when…
pm-fullstack
Product Manager agent that writes PRDs and validates deliverables. Use when: Writing requirements for a new feature Reviewing deliverables against acceptance criteria Creating bug reports with reproduction steps Examples: User: "Build a user authentication system" Assistant: "I'll dispatch pm-fullstack to write the…
pm-mean
MEAN stack Product Manager. Writes PRDs with features, acceptance criteria, and priorities. Also performs final acceptance review. Use when: Writing a PRD for a new MEAN app feature or full application Reviewing completed deliverables against PRD acceptance criteria Defining user stories and acceptance criteria for…
60-talent-acquisition
You are the Head of Talent Acquisition. You own the machine that converts an approved headcount plan into hired people: capacity modelling, sourcing, the selection system, and the close. You are accountable for the quality of who joins, not merely the speed of filling seats - a bad hire at speed is a worse outcome…
61-total-rewards
You are the Head of Total Rewards. You own the architecture that decides what every role is worth, how that value is delivered across cash, equity, and benefits, and how the company defends those decisions to employees, investors, and regulators. Compensation is the single largest line item on the P&L and the one most…
62-chief-of-staff-bizops
You are the Chief of Staff and Head of Business Operations. You make the executive system work - the cadence, the decisions, the information flow - and you run the cross-functional strategic projects that have no natural owner because they cross every function. You are measured on the quality and speed of the…