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 commands/kirkruglov/claude-project-manager/init-projectgit clone --depth 1 https://github.com/KirKruglov/claude-project-managerWrote 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/commands/kirkruglov/claude-project-manager/init-project)<a href="https://agentmods.dev/commands/kirkruglov/claude-project-manager/init-project"><img src="https://agentmods.dev/badge/commands/kirkruglov/claude-project-manager/init-project.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 | $0.00010 | $0.01691 |
| Opus 5 | $0.00005 | $0.00846 |
| Sonnet 5 | $0.00002 | $0.00338 |
| Haiku 4.5 | $0.00001 | $0.00169 |
Grade A, and why
init-project 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 5d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Initialize Project
Create a complete project scaffold with folder structure, configuration files, and automated scheduled tasks.
Input
- project-name (required): Name of the project
- project-description (optional): Brief description of what the project is about
- starting-phase (optional): Which phase to start in (1-5, default: 1)
Process
1. Gather Project Information
Ask the user for:
- Project name (if not provided in argument)
- Brief description of the project scope and goals
- Starting phase (default to Phase 1 if not specified)
- Confirm phase details before proceeding
2. Read Project Structure Template
Read references/project-structure.md to understand the folder layout and file structure.
3. Create Folder Structure
Create the following directory structure in ${project-root}/:
project-name/
├── 01-initiation/
├── 02-planning/
├── 03-execution/
├── 04-closure/
├── meetings/
├── reports/
├── input/
└── logs/
Create subdirectories as specified in project-structure.md reference.
4. Generate CLAUDE.md
Create ${project-root}/CLAUDE.md with:
---
role: AI Project Manager Agent
project-name: [USER PROVIDED NAME]
project-description: [USER PROVIDED DESCRIPTION]
current-phase: [STARTING PHASE]
---
# Project Configuration
## References
- Orchestration Map: references/orchestration-map.md
- Agent Rules: references/agent-rules.md
- Email Autonomy Rules: references/email-autonomy-rules.md
## Orchestration Rules
After each skill execution:
1. Update project-state.md with artifact status and metadata
2. Check dependencies against orchestration-map.md
3. Identify blocked vs. available next steps
4. Suggest next step to user
5. Log action in logs/log.md with timestamp, artifact, status
## File Structure Rules
- Input data: Place in input/ folder (read-only)
- Generated artifacts: Place in numbered phase folders (01-, 02-, etc.)
- Meeting notes: Place in meetings/ folder
- Reports: Place in reports/ folder
- Logs: Append to logs/log.md
## Logging Rules
Every action logged as:
[TIMESTAMP] | [ARTIFACT] | [STATUS] | [NOTES]
## Constraints
- Do NOT modify files in input/ folder
- Do NOT make decisions that require user approval without asking
- Email autonomy levels defined in email-autonomy-rules.md
- Respect project dependencies in orchestration-map.md
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.
- 5d ago First seen · 210 lines · 10 tokens per session scan A 2d92fa953d32
init-project is a command published in the GitHub repository KirKruglov/claude-project-manager (6 stars, last pushed 4mo ago), licensed MIT. It adds 10 tokens to every session and 1,691 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 2026-08-31.
Other commands, from other repositories
contract-summary
Create contract review summaries highlighting key terms, obligations, risks, and unusual provisions.
demand-letter
Generate demand letters with legal framework, factual basis, and remedy sought.
motion-draft
Template-driven motion drafting (MTD, MSJ, motions in limine) with citation slots and jurisdiction rules.
client-memo
Draft intake memos and case assessment summaries with legal analysis.
medical-necessity
Generate medical necessity letters citing chiropractic clinical guidelines for insurance authorization and appeals.
pi-narrative
Draft personal injury and auto accident clinical narratives with mechanism of injury, treatment timeline, and causation analysis.