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 skills/kevinzai/commander/ccc-plannpx skills add KevinZai/commander --skill ccc-plangit clone --depth 1 https://github.com/KevinZai/commanderWrote 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/kevinzai/commander/ccc-plan)<a href="https://agentmods.dev/skills/kevinzai/commander/ccc-plan"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/ccc-plan.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 | $0.00034 | $0.03623 |
| Opus 5 | $0.00017 | $0.01811 |
| Sonnet 5 | $0.00007 | $0.00725 |
| Haiku 4.5 | $0.00003 | $0.00362 |
Grade A, and why
ccc-plan 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.
How it starts
The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$ccc-plan — Feature Planning Flow
User has an idea. Job: turn it into a structured plan file before any code gets written. We cascade through a spec interview, then fire the planner agent in the background to produce the plan at the session-bound path returned by EnterPlanMode — so it renders in Claude Code Desktop's native Plan pane. Return a one-line summary + path.
This is the "evals before specs before code" gate. Every multi-day feature routes through here.
Step 0 — Detect and enter plan mode (ALWAYS first)
Before showing any UI, determine the session plan file path:
If "Plan File Info" block is present in the system-reminder context (Desktop already activated plan mode for this session, surfacing a path like ~/.claude/plans/<whimsy-name>.md):
- Capture that path as
PLAN_PATH - Do NOT call
EnterPlanModeagain — it is already active
If NO "Plan File Info" block is detected:
- Call the
EnterPlanModetool — this switches the session into plan mode EnterPlanModereturns the session-bound path (e.g.,~/.claude/plans/spirited-oak-forest.md)- Capture that returned path as
PLAN_PATH
PLAN_PATH is the canonical write target for the rest of this skill. Do not write to any other path under ~/.claude/plans/.
Why this matters: Desktop's native Plan pane only reads the session-bound path it created. Writing to a fixed
~/.claude/plans/ccc-<date>-<slug>.mdpath produces a plan the pane cannot find — it shows "no plan yet" even after the skill runs.
Step 1 — Mark chapter
Call mcp__ccd_session__mark_chapter with:
title:"Feature planning"summary: one-line summary of what the user wants to plan (infer from any argument passed, or use "Structured feature plan" if unknown yet)
Response shape (EVERY time, after steps 0-1)
Output exactly these three sections in order:
1. Brand header (one line, markdown)
**CC Commander** · v{VERSION} · Planner · spec-first, plan-before-code
Read VERSION from ${CLAUDE_PLUGIN_ROOT}/.codex-plugin/plugin.json.
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 · 314 lines · 34 tokens per session scan A 03c1eb6c03eb
ccc-plan is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 3,623 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 skills, from other repositories
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
map-fast
Minimal workflow for small, low-risk changes — no planning, no learning.
airtable-webhooks
Receive and verify Airtable webhooks. Use when setting up Airtable webhook handlers, debugging X-Airtable-Content-MAC signature verification, handling the thin-ping notification, or fetching base changes (tableData, tableFields, tableMetadata add/remove/update) from the webhook payloads API.