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 commands/johnnywuj81/tokenknows/kggit clone --depth 1 https://github.com/johnnywuj81/tokenknowsWrote 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/commands/johnnywuj81/tokenknows/kg)<a href="https://agentmods.dev/commands/johnnywuj81/tokenknows/kg"><img src="https://agentmods.dev/badge/commands/johnnywuj81/tokenknows/kg.svg" alt="Measured on agentmods" 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 | $0.00054 | $0.00403 |
| Opus 5 | $0.00027 | $0.00201 |
| Sonnet 5 | $0.00011 | $0.00081 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
kg scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
按 tokenknows:distill skill 的标准流程,把当前 session 蒸馏成 knowledge_graph:
KG 关键价值:
- 跨实体关系一目了然 (谁推动了什么 / 什么依赖什么 / 哪些决策冲突)
- 跨文档实体合并 (Alice 在多个 KG 里自动合一)
- 浏览器内可视化拖拽探索
适合用 KG 的对话:
- 涉及 多人, 多决策, 多文档/工具
- 故障复盘 + 后续修复 (caused_by 链)
- 季度回顾 / 大项目 wrap-up
- 拆 event 时给每个实体清晰锚定 (谁 / 什么时候 / 做了什么) - 后端会基于此抽节点
submit_session_eventsdistill_document(document_type="knowledge_graph", time_window=$ARGUMENTS 默认 last_30_days)- 轮询完成
- 展示:
- 节点数 / 边数 / 4 类节点分布
- 用 ASCII art 示意一两条关键关系 (e.g.
Alice --authored_by--> PR#127 --depends_on--> retry_jitter) - 给浏览器 URL 让用户看完整可视化 (view_url 是绝对 URL, 前缀由 TOKENKNOWS_WEB_BASE 决定; 需登录 Web 工作台)
- 如果用户问 "X 在哪些文档里也出现", 调
search_entity(query="X")
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.
- 3d ago First seen · 26 lines · 54 tokens per session scan A 63dd8aae1612
kg is a command published in the GitHub repository johnnywuj81/tokenknows (4 stars, last pushed 15d ago), licensed MIT. It adds 54 tokens to every session and 403 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 2026-08-31.
Other commands, from other repositories
save-session-learnings
Document session learnings to CLAUDE.md and AGENTS.md. Use after completing significant tasks, debugging sessions, or discovering project patterns.
kiro-steering-custom
Command "kiro-steering-custom" from gotalab/cc-sdd, covering kiro custom steering creation, workflow, available templates, steering principles and tool guidance.
memory-why
Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.
wiki-synthesize
Synthesize wiki/sources/ .md pages from raw session transcripts using the configured LLM backend.
review-code
Read ALL memory bank code rules + best practices, check the files that changed, and APPLY fixes so they adhere. The active counterpart to /scan (which is read-only). Use after an AI session, before commit, to make changed files compliant.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.