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/chtnnh/know-code/know-code-teachnpx skills add chtnnh/know-code --skill know-code-teachgit clone --depth 1 https://github.com/chtnnh/know-codeWhat 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 | $0.00077 | $0.00835 |
| Opus 5 | $0.00039 | $0.00417 |
| Sonnet 5 | $0.00015 | $0.00167 |
| Haiku 4.5 | $0.00008 | $0.00084 |
Grade A, and why
know-code-teach 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 yesterday.
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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
know-code-teach
Teach the human what is changing and why — before you edit files, then keep teaching in small increments while you code. This skill never writes a know-code gate receipt. Verification is know-code.
When to run (required)
Run this skill before you create or modify project files for any non-trivial task:
- New features, refactors, bug fixes that touch more than a one-liner
- Session start on an unfamiliar codebase / area
- After a know-code gate deny (before
know-codequiz) - After a quiz failure (re-teach weak spots)
- User asks “what are you doing?”, “why this approach?”, or “catch me up”
Skip only if the human explicitly says so (“skip teach”, “just do it”, “I know this”).
Playbook
Read references/explain-playbook.md and follow it. Defaults:
- Intent — one sentence: problem + proposed outcome
- Touch map — which areas of the codebase will change (paths/modules)
- Approach — chosen design in plain language
- Trade-offs — 1–3 alternatives and why not
- Risks — what could go wrong; what you will verify
- Checkpoint — ask if the human wants a different approach before editing
While coding, keep explanations incremental: after meaningful chunks, narrate what landed and what is next. No lectures. No wall of text.
Pairing with know-code
| Skill | Role |
|---|---|
know-code-teach |
Build understanding before/during work |
know-code |
Verify understanding before commit/push/PR |
Required order: range begin → teach → implement and stage the final diff → human seals know-code taught → questions → quiz → ask → agent grade-proposal.json → human grade --review → pass → know-code commit → range seal / push.
Re-seal know-code taught when the diff hash changes (know-code hash).
After teaching, implementation, and staging (or an explicit human skip), the human seals the final artifact (passphrase; agents cannot forge):
know-code taught
# or, only if the human explicitly skipped:
know-code taught --skip
What ships with it
1 file 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.
- yesterday First seen · 76 lines · 77 tokens per session scan A 9dbdc7b1f9e6
know-code-teach is a skill published in the GitHub repository chtnnh/know-code (3 stars, last pushed yesterday), licensed MIT. It adds 77 tokens to every session and 835 once invoked, about $0.0004 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
create-skill
Guides users through creating effective Agent Skills for Cursor. Use when the user wants to create, write, or author a new skill, or asks about skill structure, best practices, or SKILL.md format.
ppt-design
使用 HTML 设计与生成高质量演讲幻灯片（PPT/Deck）。当用户希望生成、设计、修改幻灯片、deck、slides、presentation、汇报、提案、pitch、课件时触发。主干：1280×720px 可编辑 HTML 幻灯片 + 唯一 editable HTML→EditableSlideScene→OOXML 管线 + 数据/信息可视化意识 + 5 种设计哲学 + 反 AI slop + 单页自包含 slide-XX.html。不生图；缺图用可编辑原语或占位并标注建议补图。.
hns-lsel-curator
Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
skill-creator
Create, refine, and benchmark agent skills. Use when building a new skill, updating an existing one, running evals, checking trigger quality, or improving a skill description.
memstack-development-mentor
Use when the user says 'teach me', 'explain as you go', 'mentor mode', 'walk me through', 'help me learn', 'explain why', 'learning mode', or wants real-time plain language narration of decisions and tradeoffs while building. Do NOT use for code review or debugging.