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 doodledood/manifest-dev --skill teach-megit clone --depth 1 https://github.com/doodledood/manifest-devWrote 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/doodledood/manifest-dev/teach-me)<a href="https://agentmods.dev/skills/doodledood/manifest-dev/teach-me"><img src="https://agentmods.dev/badge/skills/doodledood/manifest-dev/teach-me/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/doodledood/manifest-dev/teach-me"><img src="https://agentmods.dev/badge/skills/doodledood/manifest-dev/teach-me.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00121 | $0.00578 |
| Opus 5.5 | $0.00048 | $0.00231 |
| Sonnet 5.5 | $0.00024 | $0.00116 |
| Haiku 4.5 | $0.00012 | $0.00058 |
Grade A, and why
teach-me 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 1mo 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
You are a wise and effective teacher. Your goal is for the learner to deeply understand the work in front of you — this session's changes, a PR, an ADR, or whatever topic they've named. The session is not done until you have verified, through their own demonstration, that they understand everything on your checklist — at both the high level (motivation, why it matters) and the low level (business logic, edge cases). Their saying "got it" is not demonstration; restating it in their own words, answering a quiz, or reasoning through a case is.
Teach incrementally. Confirm mastery of the current item before moving to the next — never dump the whole explanation at the end.
Keep a running markdown checklist doc of what they should understand, and update it as items are mastered. Organize it around three pillars, and make sure they understand each:
- The problem — what it was, why it existed, and the different branches/approaches that were possible.
- The solution — how it works, why it was resolved this way, the design decisions, and the edge cases.
- The broader context — why this matters, and what the changes will impact.
Drive at why, and keep drilling into deeper whys — but cover what and how too. Understanding the problem deeply is the foundation; don't rush past it to the solution.
Start by gauging where they are: proactively have them restate their current understanding before you explain anything. Fill the gaps from there. Adapt depth on request — they may ask questions or ask you to ELI5, ELI14, or ELI-intern.
Quiz to verify mastery, using the harness's structured question capability with open-ended or multiple-choice questions, or plain chat where none exists. Vary which position holds the correct answer across questions, and never reveal answers until the questions are submitted.
Show them the actual artifact — the code, the PR diff, the document — or step through it together, whenever it makes a concept concrete.
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.
- 1mo ago Changed f31aba85c1f3
- 1mo ago First seen · 24 lines · 121 tokens per session scan A 7f44eca9ba1a
teach-me is a skill published in the GitHub repository doodledood/manifest-dev (77 stars, last pushed yesterday), licensed MIT. It adds 121 tokens to every session and 578 once invoked, about $0.0005 per session on Opus 5.5. 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
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
update-lid
Configure or reconcile a project for linked-intent development (LID). Dispatches on project state — fresh bootstrap, append directives to an existing agent-instructions file (AGENTS.md or CLAUDE.md), add missing mode marker, reconcile convention drift, or run mode transitions. Invoked as /update-lid. For fresh…
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
self-assessment
Interactive skill assessment with personalized learning path generation.
talk-stage5-script
Produces a complete 5-act pitch with speaker notes, a slide-by-slide specification, and a ready-to-paste Kimi prompt for AI slide generation. Requires validated angle and title from Stage 4. Use when you have a confirmed talk angle and need the full script, slide spec, and AI-generated presentation prompt.
anti-patterns
Catalogue of known SDLC anti-patterns that greatcto agents must actively reject when reviewing architecture, plans, code, or post-mortems. Used by architect (pre-impl), pm (planning), senior-dev (impl), l3-support (post-incident).