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 qkitzero/kage-bunshin --skill learninggit clone --depth 1 https://github.com/qkitzero/kage-bunshinWrote 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/qkitzero/kage-bunshin/learning)<a href="https://agentmods.dev/skills/qkitzero/kage-bunshin/learning"><img src="https://agentmods.dev/badge/skills/qkitzero/kage-bunshin/learning/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/qkitzero/kage-bunshin/learning"><img src="https://agentmods.dev/badge/skills/qkitzero/kage-bunshin/learning.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 | $0.00045 | $0.00823 |
| Opus 5 | $0.00023 | $0.00411 |
| Sonnet 5 | $0.00009 | $0.00165 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
learning 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 9d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learning Skill
A workflow that creates an Agent Team of Researcher and Analyst to perform structured retrospectives through evidence-based analysis and discussion.
Workflow
Step 1: Understand the Retrospective Target
Accurately understand the retrospective target presented by the user. Clarify:
- Subject (project, sprint, decision, event, etc.)
- Time period (from when to when)
- Stakeholders & context
- Original goals & expectations
Use open questions to help the user elaborate on details.
Step 2: Retrieve Past Notebook Context
If NOTEBOOK_PATH is set, search for past lessons related to the retrospective target:
- Grep
$NOTEBOOK_PATH/learnings/and$NOTEBOOK_PATH/research/for keywords from the target (searching title, tags, and body) - Read up to 3 matching entries (frontmatter + first 200 characters of body)
- Include the retrieved content as context when creating the team
Skip this step if zero matches or NOTEBOOK_PATH is not set.
Step 3: Create Agent Team
Create a team with the following teammates using their agent definitions from .claude/agents/:
Teammates:
researcher— gathers evidence, data, and context about what happenedanalyst— performs structured retrospective analysis
Team instructions:
Retrospective target: [Subject]
Time period: [Period]
Original goals: [Goals and expectations]
[Past Notebook context if found]
Collaboration protocol:
1. Researcher gathers evidence: project history, outcomes, metrics, related context from Notebook and codebase
2. Analyst performs initial retrospective analysis (what went well, what didn't, patterns, key learnings)
3. Researcher challenges the analysis — verifies claims against evidence, surfaces overlooked factors
4. Analyst refines the analysis based on Researcher's input, deepens root cause analysis
5. Continue iterating until both agree the lessons are well-evidenced and actionable (aim for 2-3 rounds)
Rules:
- Output language: Use the language specified by OUTPUT_LANGUAGE env var. If not set, match the user's language (default: English)
- If NOTEBOOK_PATH is set: Researcher saves evidence summary to $NOTEBOOK_PATH/research/, Analyst saves retrospective to $NOTEBOOK_PATH/learnings/
- Each agent writes its own deliverables with structured frontmatter (Analyst must use type: learning)
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.
- 9d ago First seen · 116 lines · 45 tokens per session scan A aafc1f07df5a
learning is a skill published in the GitHub repository qkitzero/kage-bunshin (1 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 823 once invoked, about $0.0002 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
educational-presentation
Crea presentazioni interattive per lezioni scolastiche ITIS usando React via CDN, dark theme, simulatori interattivi, e quiz. Due approcci consolidati: CDN-based (zero build, HTML puri) e Build-based (Vite+TS+Tailwind). Deploy su GitHub Pages. Progetto di riferimento: presentazione-vpn (Mar 2026).
ctf-misc
Provides miscellaneous CTF challenge techniques for problems that do not cleanly fit the main categories. Use for encoding puzzles, pyjails, bash jails, RF/SDR, DNS oddities, unicode tricks, esoteric languages, QR or audio puzzles, constraint solving, game theory, unusual sandbox escapes, and hybrid logic puzzles.…
slide-excellence
Multi-agent comprehensive slide review (visual + pedagogy + proofreading, plus TikZ / parity / substance conditionally). Use when user says "full review", "excellence pass", "comprehensive check", "review everything", "pre-release review", "slide excellence", or before teaching / shipping a deck. Fanout wrapper — for…
respond-to-eval
Turn student course evaluations (free-text + numeric) into an actionable teaching-improvement plan — the teaching analogue of /respond-to-referees. Clusters comments into themes, separates signal from noise, classifies each theme Keep / Change / Investigate / Out-of-scope, and drafts concrete changes mapped to the…
scaffold-exercises
Scaffold a graded problem set with sections, problems, worked solutions, and short "why this matters" explainers across analytical, empirical, and coding types. Use when user says "make a problem set on X", "scaffold exercises for this lecture", "create practice problems", "generate homework with a solution key"…
create-lecture
Create a new Beamer lecture .tex from source papers and materials, with notation consistency checks and the project's preamble wired in. Use when user says "create a lecture on X", "new lecture from these papers", "start a deck on topic Y", "scaffold a new Beamer file", "build me a lecture from these PDFs". Scaffolds…