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 mgiovani/cc-arsenal --skill project-plannergit clone --depth 1 https://github.com/mgiovani/cc-arsenalWrote 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/mgiovani/cc-arsenal/project-planner)<a href="https://agentmods.dev/skills/mgiovani/cc-arsenal/project-planner"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/project-planner/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/mgiovani/cc-arsenal/project-planner"><img src="https://agentmods.dev/badge/skills/mgiovani/cc-arsenal/project-planner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00112 | $0.02148 |
| Opus 5.5 | $0.00045 | $0.00859 |
| Sonnet 5.5 | $0.00022 | $0.00430 |
| Haiku 4.5 | $0.00011 | $0.00215 |
Grade A, and why
project-planner 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 21d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Planner
Break a large project into tasks with explicit dependencies, then track progress and diagram the result in Mermaid.
Project to Plan
$ARGUMENTS
Planning Workflow
This skill has exactly two possible outputs: a full plan (Phases 0-4), or (when the scope fails the gate in Step 0.2) clarifying questions and nothing else. Never both in the same turn.
Portability: No Task/TaskCreate tools in this environment? Do the analysis yourself instead of delegating to an Explore agent, and track the resulting tasks as a plain markdown checklist (- [ ] Task name, blocked by: ...) instead of TaskCreate calls. The phases and the dependency diagram are the deliverable; the Task tool is just Claude Code's way of tracking them. In an eval or sandbox run, never call the real session Task/TaskCreate/TaskUpdate/TaskList tools: those mutate the operator's actual task list. If the prompt instead asks you to record intended calls into a file (e.g. outputs/tasks.json), do that instead and treat it as the graded deliverable.
Phase 0: Project Analysis
Step 0.1: Understand Project Scope
Use a Haiku-powered Explore agent for token-efficient codebase analysis:
Use Task tool with Explore agent:
- prompt: "Analyze the project to understand:
1. Read CLAUDE.md and README.md for project context
2. Identify project type (web app, API, CLI, library, etc.)
3. Map out major components and modules
4. Note technology stack and frameworks
5. Identify existing patterns and conventions
6. Find similar completed features to reference
Return a structured summary of the project architecture."
- subagent_type: "Explore"
- model: "haiku" # Token-efficient for exploration
Step 0.2: Scope Gate
Check whether the request names a concrete deliverable and rough boundaries (what's in, what's out). If it doesn't (e.g. "improve the app", "make things better", "plan our roadmap" with no target named), stop. End the response with 2-3 clarifying questions (via AskUserQuestion or plain prose) about the concrete deliverable, scope boundaries, or target outcome. Produce no task breakdown, no TaskCreate calls, no Mermaid diagram, and no files. Skipping the question is the costlier path: a 25-task plan built on invented scope forces the user to audit every task against what they actually meant, when answering the question up front would have taken seconds. Do not soften this into "ask, then proceed with reasonable assumptions anyway": the questions are the entire response.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 21d ago Changed · -2 lines 1152c3021ebd
- 1mo ago Changed · +3 lines 59b5a3b5716c
- 1mo ago Changed · +1 lines b4b763f3b09a
- 1mo ago First seen · 152 lines · 112 tokens per session scan A fb89434f8962
project-planner is a skill published in the GitHub repository mgiovani/cc-arsenal (8 stars, last pushed 2d ago), licensed MIT. It adds 112 tokens to every session and 2,148 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
handoff-protocols
Manages work transitions between team members or agents by creating structured handoff documents, summarizing project status, documenting key decisions, blockers, and open questions, and generating onboarding briefs. Use when someone needs to hand off, hand over, or transition a project; pass work to another person or…
gitlab
Agent-callable GitLab tools — manage issues and merge requests, review diffs, commit files, run pipelines, and search. Use when the user mentions GitLab or wants to review or merge an MR, commit code, run CI, or manage issues — even if they don't name GitLab explicitly.
harvest
Agent-callable Harvest tools — track time (log hours, start/stop timers), and manage the projects, clients, contacts, and tasks time is logged against, plus read invoices and account settings. Use when the user wants to log or edit time, manage Harvest projects/clients/tasks, or check what was billed — even if they…
linear
Agent-callable Linear tools — create, update, find, and comment on issues; manage projects; and resolve teams, states, labels, users, and cycles. Use when the user mentions Linear or wants to track issues, even if they don't name Linear explicitly.
quality
Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.
follow-up-after-call
Use after a completed customer, prospect, partner, or important internal sales call, discovery session, demo, or conversation, including when the user supplies or uploads a transcript, notes, recording summary, or other grounded evidence. Advise on, assess, qualify, recap, and produce seller-ready follow-up actions…