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-knowledgenpx skills add KevinZai/commander --skill ccc-knowledgegit 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 | $0.00040 | $0.01234 |
| Opus 5 | $0.00020 | $0.00617 |
| Sonnet 5 | $0.00008 | $0.00247 |
| Haiku 4.5 | $0.00004 | $0.00123 |
Grade B, and why
ccc-knowledge 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -rl "KEYWORD" ~/.claude/commander/knowledge/ 2>/dev/null How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$ccc-knowledge — Knowledge compounding
Placeholders like ~~knowledge base refer to connected tools. See CONNECTORS.md.
Search and surface lessons from the CC Commander knowledge base at ~/.claude/commander/knowledge/. Lessons are captured by the knowledge-capture hook (file-level edits) and manual entries created via this skill — no manual input required for basic capture.
Quick Mode (default)
Show the 3 most recent lessons and offer to search or browse:
ls -t ~/.claude/commander/knowledge/*.json 2>/dev/null | head -3
Read each file, display one line per lesson:
[2026-04-10] web | success — Build Next.js dashboard with Tremor charts
[2026-04-09] api | error — Stripe webhook signature validation failed
[2026-04-08] cli | success — Build RTK proxy CLI with Rust + clap
Then ask via AskUserQuestion:
- "Search by topic"
- "Show all recent lessons (10)"
- "Browse by category"
- "View stats"
- "Back to main menu"
Power Mode
Full browse, search, and filter. Activate by passing --power or browse as argument.
Search by Topic
grep -rl "KEYWORD" ~/.claude/commander/knowledge/ 2>/dev/null
Read matching files. Extract description, outcome, successPatterns, errorPatterns. Format:
[2026-03-15] web | success
Task: Build Next.js dashboard with auth
Worked: shadcn/ui init before Tremor, use server actions for mutations
Failed: n/a
Stack: Next.js 14, TypeScript, Prisma, NextAuth
Example queries: "next.js" → Next.js lessons | "auth" → JWT/OAuth lessons | "timeout" → timeout failures | "postgres" → DB lessons
Recent Lessons (10)
ls -t ~/.claude/commander/knowledge/*.json 2>/dev/null | head -10
Display: [timestamp] category | outcome — task description (60 chars max)
Stats
ls ~/.claude/commander/knowledge/*.json 2>/dev/null | wc -l
grep -rl '"outcome":"success"' ~/.claude/commander/knowledge/ 2>/dev/null | wc -l
grep -rl '"outcome":"error"' ~/.claude/commander/knowledge/ 2>/dev/null | wc -l
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 · 145 lines · 40 tokens per session scan B e640aec4d929
ccc-knowledge is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 1,234 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
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.
agent-workspace-linux
Use when a task needs an isolated hidden Linux desktop or workspace-owned browser: GUI app QA, web/browser/shopping automation, sandboxed app observation, or stale workspace cleanup. Routes agent-workspace-linux MCP tools on demand. Does NOT apply to host desktop/Chrome control, generic MCP setup, or pure code/file…
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。.
map-review
Interactive 4-section code review using monitor, predictor, and evaluator agents plus the user and maintainer role reviewers on current changes. Use when reviewing a diff, PR, or staged work before merge. Do NOT use to plan or implement; use map-plan or map-efficient.