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 zszz3/AgentRecall --skill one-bite-teachinggit clone --depth 1 https://github.com/zszz3/AgentRecallWrote 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/zszz3/agentrecall/one-bite-teaching)<a href="https://agentmods.dev/skills/zszz3/agentrecall/one-bite-teaching"><img src="https://agentmods.dev/badge/skills/zszz3/agentrecall/one-bite-teaching/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/zszz3/agentrecall/one-bite-teaching"><img src="https://agentmods.dev/badge/skills/zszz3/agentrecall/one-bite-teaching.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 | $0.00106 | $0.01378 |
| Opus 5.5 | $0.00042 | $0.00551 |
| Sonnet 5.5 | $0.00021 | $0.00276 |
| Haiku 4.5 | $0.00011 | $0.00138 |
Grade A, and why
one-bite-teaching 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
One-Bite Teaching
Teach so the learner can later explain it themselves, out loud, without notes. This is a two-phase skill: first find the key points from real sources, then deliver them one bite at a time. Skipping phase one produces confident, well-formatted teaching of things that are wrong or not actually central — the worst outcome.
Phase 1 — Find the key points first (before teaching anything)
You cannot teach the essence of a project you have only skimmed. Extract it from real sources first:
- Map before you drill. Get the shape — modules, entry points, the main flow, input→output — before opening any single file deeply. Hold a one-paragraph "what is this" before going deep on any part.
- Find the load-bearing designs, not a feature list. The essence is the few decisions everything hinges on and the WHY behind them (the trade-off, the failure mode they prevent). Rank candidates by "if this were wrong, how much breaks." A feature inventory is not understanding.
- Mine comments and docs for the "why" and the evidence. The highest-signal spots are where the code deliberately does NOT do the obvious thing and a comment says why — often with measured rationale (a threshold, an "X of Y cases" number, a calibration note). Those explain why a value is what it is.
- Verify every claim against the real source; separate confirmed from inferred. Read the actual code / doc / git history / chat, don't reason from the name. Never smooth a gap with a plausible guess — the learner may repeat it under questioning. Label inference as inference.
- Numbers need provenance and a denominator. A metric isn't learned until you know where it came from and what it's over (4/736, not just "0.5%"). Trace it to its source doc/run.
- Attribute ownership honestly. In shared projects, use git/doc authorship to separate what the learner did from what the team did. Don't let them absorb others' work — it collapses under one follow-up.
- Hunt the pitfalls and counter-intuitive parts. The traps and the "we deliberately don't do X because…" decisions are the highest-value things to understand and the most likely to be asked about.
What ships with it
2 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.
- 1mo ago First seen · 59 lines · 106 tokens per session scan A 45da4f765519
one-bite-teaching is a skill published in the GitHub repository zszz3/AgentRecall (594 stars, last pushed today), licensed MIT. It adds 106 tokens to every session and 1,378 once invoked, about $0.0004 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.