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-eccnpx skills add KevinZai/commander --skill ccc-eccgit 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 | $0.00035 | $0.01403 |
| Opus 5 | $0.00017 | $0.00701 |
| Sonnet 5 | $0.00007 | $0.00281 |
| Haiku 4.5 | $0.00003 | $0.00140 |
Grade A, and why
ccc-ecc 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 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.
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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$ccc-ecc — Selective ECC Loader
Load one specific Everything Claude Code (ECC) component into ~/.claude/ without copying the whole ECC harness.
ECC source lives at vendor/everything-claude-code/. This is a click-first picker: choose a skill, agent, or hook; then symlink or copy only that component.
Safety model
- Prefer symlink so updates follow the pinned ECC vendor checkout.
- Offer copy for an editable local snapshot.
- Back up before replacing anything under
~/.claude/. - Never install ECC settings, commands, or the full harness.
Steps
1. Locate ECC
git rev-parse --show-toplevel
test -d vendor/everything-claude-code && echo ok || echo missing
If missing, stop with:
ECC vendor checkout not found at
vendor/everything-claude-code/. Run$ccc-upgradeor initialize submodules first.
2. Ask what to do
question: "What ECC component do you want to load?"
header: "ECC"
multiSelect: false
options:
- label: "Load a skill"
- label: "Load an agent"
- label: "Load a hook"
- label: "List available ECC components"
3. Inventory candidates
ECC="vendor/everything-claude-code"
find "$ECC" \( -path '*/node_modules/*' -o -path '*/.git/*' -o -path '*/dist/*' -o -path '*/build/*' \) -prune -o \
\( -path '*/skills/*/SKILL.md' -o -path '*/agents/*.md' -o -path '*/hooks/*.js' -o -path '*/hooks/*.sh' \) -print
Classify skills/<name>/SKILL.md as skills, agents/*.md as agents, and hooks/*.{js,sh} as hooks. If the user chose "List available", render grouped markdown tables and stop.
4. Ask which component — two-level AUQ cascade, never a typed-name table
ECC ships 156+ skills — never dump them into one picker (max 4 options) and never fall back to "type the exact name" as a first resort; that reintroduces the numbered-list anti-pattern this plugin exists to avoid.
Level 1 — category. If the matched candidates (skills, agents, or hooks) number more than 4:
- If they group meaningfully by directory prefix (e.g.
skills/testing/*,skills/security/*), present up to 3 category buckets + "More categories…" as anAskUserQuestion(≤4 options). - Otherwise (a flat namespace), bucket alphabetically into roughly-equal groups computed from the actual candidate count (e.g. ~4 buckets sized
ceil(N/4)each) and present those buckets as the picker — do not hardcode fixed letter ranges like "A-F"; they skew badly on a real name distribution.
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 · 140 lines · 35 tokens per session scan A 3f35b83172f4
ccc-ecc is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 1,403 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.
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。.