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 skills add owenliang60-ship-it/knowledge-mgmt --skill reviewgit clone --depth 1 https://github.com/owenliang60-ship-it/knowledge-mgmtWrote 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/owenliang60-ship-it/knowledge-mgmt/review)<a href="https://agentmods.dev/skills/owenliang60-ship-it/knowledge-mgmt/review"><img src="https://agentmods.dev/badge/skills/owenliang60-ship-it/knowledge-mgmt/review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/owenliang60-ship-it/knowledge-mgmt/review"><img src="https://agentmods.dev/badge/skills/owenliang60-ship-it/knowledge-mgmt/review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00067 | $0.03427 |
| Opus 5 | $0.00034 | $0.01714 |
| Sonnet 5 | $0.00013 | $0.00685 |
| Haiku 4.5 | $0.00007 | $0.00343 |
Grade A, and why
review 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 10d 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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review Command
间隔重复复习系统 — 用 FSRS-6 算法复习 Obsidian 中的原子卡片（石头）。
定位
研究 → /note 存卡 → /review 复习 → 知识巩固
| Skill | 职责 | 输出 |
|---|---|---|
/note |
知识沉淀 — 研究摘要 + 原子卡片 | Obsidian 卡片组 |
/review |
知识巩固 — 间隔重复复习 | 本地 review_state.json |
/journal |
进度记录 — 做了什么 | 本地 journal + Obsidian journal |
文件路径
- Claude Code skill 目录:
$HOME/.claude/skills/review/ - Codex skill 目录:
$HOME/.agents/skills/review/ - FSRS 引擎:
- Claude Code:
$HOME/.claude/skills/review/scripts/fsrs_engine.py - Codex:
$HOME/.agents/skills/review/scripts/fsrs_engine.py
- Claude Code:
- 状态文件默认位置:
- Claude Code:
${KM_REVIEW_STATE_PATH:-$HOME/.claude/skills/review/review_state.json} - Codex:
${KM_REVIEW_STATE_PATH:-$HOME/.agents/skills/review/review_state.json}
- Claude Code:
运行时约定（Claude Code / Codex）
下文所有命令里的两个占位按当前运行时替换：
<FSRS_ENGINE_PATH>- Claude Code:
$HOME/.claude/skills/review/scripts/fsrs_engine.py - Codex:
$HOME/.agents/skills/review/scripts/fsrs_engine.py
- Claude Code:
<REVIEW_STATE_PATH>- 默认就是对应 skill 目录下的
review_state.json - 如需自定义，优先用
KM_REVIEW_STATE_PATH
- 默认就是对应 skill 目录下的
配置：状态文件路径
默认状态文件位置与 installed skill 同目录：
- Claude Code:
~/.claude/skills/review/review_state.json - Codex:
~/.agents/skills/review/review_state.json
如需自定义（例如跨机器同步、多 vault 隔离、测试隔离），通过环境变量覆盖：
export KM_REVIEW_STATE_PATH=/path/to/your/review_state.json
本 skill 内所有 fsrs_engine.py 的调用都会展开这个变量，自动使用自定义路径。不 export 时使用默认路径。
Usage
Claude Code 通常直接写 /review。Codex 可显式写 $review（或用自然语言让 Codex 按 skill 描述隐式匹配）。
/review # 扫描 + 复习（默认）
/review --mode=scan # 仅扫描新卡片，不复习
/review --mode=stats # 查看统计信息
/review --topic=多巴胺 # 只复习某主题
/review --limit=5 # 本次最多复习5张
Behavior
Step 1: 扫描注册新卡片
每次 /review 自动执行（除 mode=stats）。
1a. 获取当前状态
python3 <FSRS_ENGINE_PATH> <REVIEW_STATE_PATH> stats
从返回的 known_card_ids 得知已注册卡片。
1b. 列出 Cards/ 目录发现新卡片
唯一识别标准：frontmatter 含 type/atomic 标签 = 原子卡片。
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 369 lines · 67 tokens per session scan A 37b4ce354636
review is a skill published in the GitHub repository owenliang60-ship-it/knowledge-mgmt (37 stars, last pushed 5mo ago), licensed MIT. It adds 67 tokens to every session and 3,427 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
cortex-memory
Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection.
vault-review
Daily knowledge review — surface the notes the user is forgetting (FSRS memory decay) and the weak spots in their vault (gaps), then propose 2-3 concrete things to revisit or connect. Use when the user asks "what should I review", "what am I forgetting", or wants a knowledge check-in.
discuss-cognition
Guide an incremental, evidence-aware discussion that turns an AI, product, model-strategy, competition, or implementation topic into durable personal cognition. Use when the user wants to discuss, learn, explore, compare, challenge, or deeply understand such a topic, including a recommended daily topic. Ask one…
srsa-review
Use when running Spaced Repetition Systems for AI Agents (SRSA) daily review sessions, grading cards with again/hard/good/easy, and proposing explicit memory add/delete/update actions after each review.
autology-tutorial
Use when user is new to Autology, asks "how does Autology work", wants to learn about knowledge capture, or requests a guided introduction.
heptabase-linking
Create real cross-links between Heptabase cards via the heptabase CLI. Use when the user wants to link Heptabase cards, cross-reference notes, build a card graph, or fix existing [[Card Title]] wiki-link text that is rendering as plain text instead of a clickable card pill. Real links require a ProseMirror card node…