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-learnnpx skills add KevinZai/commander --skill ccc-learngit clone --depth 1 https://github.com/KevinZai/commanderWhat 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 | $0.00047 | $0.01790 |
| Opus 5 | $0.00023 | $0.00895 |
| Sonnet 5 | $0.00009 | $0.00358 |
| Haiku 4.5 | $0.00005 | $0.00179 |
Grade B, and why
ccc-learn scanned grade B with 1 finding 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 2d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
- `ls ~/.claude/skills/ 2>/dev/null | wc -l` — locally installed skill count How it starts
The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$ccc-learn — Discover skills across domains
Click-first browser over CCC's 11 domain routers. User picks a domain in one click — we load its domain-router skill and hand off. No text menus, no grep-through-502-skills.
Response shape (EVERY time)
1. Brand header (one line)
**CC Commander · Learn** · 502+ skills · 11 domains · [catalog](https://commanderplugin.com/skills)
2. Context strip (one line)
Run a single parallel Bash probe (silent on failure):
ls ~/.claude/skills/ 2>/dev/null | wc -l— locally installed skill counttest -f CLAUDE.md && head -2 CLAUDE.md | tail -1— project name hintgit rev-parse --abbrev-ref HEAD 2>/dev/null— branch
Render:
📚 skills installed locally · project
<name or cwd>· branch<name>
If nothing installed: "📚 No CCC skills installed yet — pick a domain, I'll fetch on demand."
3. The picker — AskUserQuestion with 4 options
Read ${CLAUDE_PLUGIN_ROOT}/menus/ccc-learn.json once. Use its choices for labels + descriptions. Max 4 options — take the 3 headline domains + "More domains…".
question: "Which domain?"
header: "CC Commander · Learn"
multiSelect: false
options:
- label: "🎨 Design (39 skills)"
description: "UI/UX, animation, responsive, a11y, Impeccable polish suite."
preview: "Routes to ccc-design. Pick landing / components / polish / figma next."
- label: "📣 Marketing (45 skills)"
description: "CRO, email, ads, social, content — 7 specialist pods."
preview: "Routes to ccc-marketing. Pick campaign / SEO / Product Hunt / influencer next."
- label: "💼 SaaS (21 skills)"
description: "Auth, billing, multi-tenant, schema, zero-to-revenue."
preview: "Routes to ccc-saas. Pick auth / billing / schema / API next."
- label: "⋯ More domains…"
description: "DevOps, SEO, Testing, Security, Data, Research, Mobile, Makeover."
preview: "8 more router skills — click to expand."
Recommendation logic (prepend ⭐ to ONE option):
- No
src/but project hasdocs/or marketing-ish files → ⭐ Marketing package.jsonhasstripe/next-auth/supabase→ ⭐ SaaSsrc/componentspopulated + Tailwind config → ⭐ Design- Nothing to go on → ⭐ Design (safe default)
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.
- 2d ago First seen · 161 lines · 47 tokens per session scan B 8719b141ec79
ccc-learn is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 1,790 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). 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.
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
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.
backend-builder
Используй только внутри активного Codex Project Autopilot-проекта по утверждённому плану; не включай для обычных backend-задач вне автопилота.
loongsuite-pilot-insight
基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用；包含 AI Coding 事件表语义，以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE，通常与 sls-dashboard-builder 一起使用。.