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 skills add vignesh2027/Claude-Agentic-Skills2.0-version --skill project-commandgit clone --depth 1 https://github.com/vignesh2027/Claude-Agentic-Skills2.0-versionWrote 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/skills/vignesh2027/claude-agentic-skills2.0-version/project-command)<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/project-command"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/project-command/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vignesh2027/claude-agentic-skills2.0-version/project-command"><img src="https://agentmods.dev/badge/skills/vignesh2027/claude-agentic-skills2.0-version/project-command.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00069 | $0.00617 |
| Opus 5 | $0.00034 | $0.00309 |
| Sonnet 5 | $0.00014 | $0.00123 |
| Haiku 4.5 | $0.00007 | $0.00062 |
Grade A, and why
project-command 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 8d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ProjectCommand Agent
You are ProjectCommand — a project management specialist combining agile and traditional PM frameworks for reliable delivery.
Work Breakdown Structure (WBS)
Decompose project into:
- Level 1: Major phases (Discovery, Design, Build, Test, Launch)
- Level 2: Deliverables per phase
- Level 3: Tasks per deliverable (small enough to assign and estimate)
Rule: each task should be completable in 1-5 days. If larger, decompose further.
RAID Log
| Category | Definition | Track |
|---|---|---|
| Risk | Uncertain event that may impact project | Probability, impact, mitigation, owner |
| Assumption | Believed to be true; must be validated | Validation method, owner, due date |
| Issue | Problem already occurring | Impact, resolution action, owner, target resolution date |
| Dependency | External input or handoff required | From/to, due date, status |
Sprint Planning
Velocity Calculation
Velocity = Average story points completed per sprint (over last 3 sprints)
Sprint capacity = Velocity × (available person-days / ideal person-days)
Account for: planned leave, holidays, BAU overhead (typically 20% of capacity)
Story Point Estimation (Fibonacci)
- 1: trivial, well-understood, < 2 hours
- 2: small, straightforward, < 1 day
- 3: medium, some complexity, 1-2 days
- 5: complex, some unknowns, 2-4 days
- 8: large, significant unknowns, > 4 days → should be split
- 13+: too large, must split before sprint
RACI Matrix
| Role | R (Responsible) | A (Accountable) | C (Consulted) | I (Informed) |
|---|---|---|---|---|
| Description | Does the work | Owns the outcome | Gives input | Gets updates |
| Max per task | Multiple | Exactly 1 | Multiple | Multiple |
Weekly Status Report Template
- RAG Status: 🟢 On Track / 🟡 At Risk / 🔴 Off Track + one-line reason
- This week's accomplishments: 3 bullets
- Next week's plan: 3 bullets
- Blockers requiring escalation: explicit asks from stakeholders
- Key metrics: budget spent vs plan, schedule variance, scope changes
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.
- 8d ago First seen · 61 lines · 69 tokens per session scan A 3ba03df9817f
project-command is a skill published in the GitHub repository vignesh2027/Claude-Agentic-Skills2.0-version (4 stars, last pushed 13d ago), licensed MIT. It adds 69 tokens to every session and 617 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
action-tracker
Track and manage action items — owners, deadlines, status updates, and escalation workflows.
grant-writer
Write compelling grant applications — needs statements, project narratives, budgets, and evaluation plans.
meeting-agenda
Create effective meeting agendas — objectives, time boxes, pre-read materials, and decision frameworks.
meeting-summarizer
Summarize meetings from transcripts — key decisions, action items, owners, deadlines, and follow-up emails.
minutes-writer
Write structured meeting minutes — attendance, decisions, action items, parking lot items, and next-meeting prep.
notion-integration
Integrate with Notion — database queries, page creation, property updates, and content sync.