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-memorynpx skills add KevinZai/commander --skill ccc-memorygit 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 | $0.00041 | $0.00796 |
| Opus 5 | $0.00020 | $0.00398 |
| Sonnet 5 | $0.00008 | $0.00159 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
ccc-memory 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
$ccc-memory — Two-Tier Persistent Memory
Claude Code sessions forget everything at the end. Memory makes the important bits stick.
When to use
- After resolving a tricky bug — save the root cause so next time the same class of issue is faster
- After making an architectural decision — record the reasoning so future-you doesn't re-argue with past-you
- When a project grows beyond one CLAUDE.md section — split into a memory/ tree
- Before a big /clear when you want to carry forward a specific insight
Not for
- Session-scoped state that ends with this session — use $ccc-save-session for that
- Searchable cross-project knowledge — use $ccc-recall for that
- Per-skill notes — put those inline in the skill's body
How it works
Two layers, different load patterns:
Layer 1 — CLAUDE.md (always-loaded)
Every file Claude reads in a session is relative to CLAUDE.md. Put here:
- Project type + tech stack (once)
- Key paths + conventions
- Commands Kevin runs daily
- Cross-cutting style rules
Keep it tight — everything here costs context on every turn.
Layer 2 — memory/ directory (on-demand)
Dated markdown files for things that don't belong in the always-loaded layer:
memory/YYYY-MM-DD-{slug}.md— daily learnings, decisions, correctionsmemory/decisions/— one file per big call (why we picked Postgres over Mongo)memory/gotchas/— known footguns (tailwind v4 syntax, framer-motion v11 rename)memory/preferences.md— curated long-term prefs that didn't fit CLAUDE.md
Load on demand by reading the specific file — Claude sees only what's needed.
Process
- Start of session:
ls memory/(if exists) → skim filenames → read the few that matter for today's task - When you learn something: add a dated entry to
memory/YYYY-MM-DD-{slug}.md - Corrections from Kevin: append to
memory/preferences.mdwith date — corrective framing ("You should X — are you doing it?") - Weekly (or before big work): consolidate — move frequently-referenced items from memory/ into CLAUDE.md; prune stale dated notes
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 · 86 lines · 41 tokens per session scan A baed629b8d07
ccc-memory is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 796 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。.