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 bang9/ai-tools --skill whip-lesson-learngit clone --depth 1 https://github.com/bang9/ai-toolsWrote 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/bang9/ai-tools/whip-lesson-learn)<a href="https://agentmods.dev/skills/bang9/ai-tools/whip-lesson-learn"><img src="https://agentmods.dev/badge/skills/bang9/ai-tools/whip-lesson-learn/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/bang9/ai-tools/whip-lesson-learn"><img src="https://agentmods.dev/badge/skills/bang9/ai-tools/whip-lesson-learn.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 | $0.00073 | $0.00805 |
| Opus 5 | $0.00036 | $0.00402 |
| Sonnet 5 | $0.00015 | $0.00161 |
| Haiku 4.5 | $0.00007 | $0.00081 |
Grade A, and why
whip-lesson-learn 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use this skill when the user wants to document a real whip run as a reusable case study, lesson learned, postmortem, or discussion draft.
Goal
Create or update a markdown file at:
.whip/lesson-learn/<file-name>.md
After writing it, tell the user the final path and a short summary of what was captured.
Language
- If the user explicitly requests a language, write in that language.
- Otherwise write in the language the user is currently using with you.
- Do not mix languages except for literal command names, file paths, or very short quoted fragments.
Prompt language rule
- If the document language and the original user prompt language differ, translate the prompt into the document language while preserving intent and important literals such as
$whip-plan,$whip-start, URLs, branch names, and issue numbers. - Only keep the original-language prompt verbatim if the user explicitly asks for verbatim preservation.
Path and naming
- Always write under
.whip/lesson-learn/. - Use the user-provided file name when given.
- If the user does not provide a file name, derive one as
YYYY-MM-DD-<short-case-name>.md. - Use lowercase hyphen-case and keep it concise.
- Create the
.whip/lesson-learn/directory if it does not already exist.
Required structure
Use these sections, translated into the chosen output language:
Used tools/사용한 도구Actual user prompts/실제 유저가 쳤던 프롬프트What the AI judged and executed/AI 가 판단하고 실행한 영역What actually happened/실제로 진행한 방향IRC coordination highlights/IRC 로 실제로 중요했던 대화Results and lessons learned/결과와 레슨런
If IRC did not matter for the case, omit section 5.
Workflow
- Gather concrete artifacts from the current run:
- user prompts
- tools and backends used
- worktree/branch/PR topology
- review findings
- IRC messages that changed decisions
- final merge and cleanup results
- Preserve literal commands and identifiers exactly.
- Distinguish initial plan from final corrected execution if the direction changed during review.
- Include only IRC messages that materially changed decisions; do not dump full transcripts.
- Keep operator mistakes and recovery steps when they are part of the lesson.
- Create or update the markdown file.
- Tell the user the path you wrote and a concise summary.
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.
- 9d ago First seen · 108 lines · 73 tokens per session scan A 59da580094f8
whip-lesson-learn is a skill published in the GitHub repository bang9/ai-tools (10 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 805 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
kanban-tui
Comprehensive kanban board and task management via ktui CLI. Use for project tracking, todo lists, task dependencies, workflow automation, and board management. Activates when user mentions boards, tasks, kanban, or project management. If the ktui command is not available, but uv is available utilize uvx kanban-tui…
quick-capture
Use this skill to drop a new task into GSD Task Manager from any AI assistant that has the gsd-mcp-server connected.
triage-inbox
Use this skill to walk the user through their unfiled or stale tasks and move them into the right Eisenhower quadrant.
agentrq
Execute tasks assigned by humans or supervisor agents within a specific AgentRQ workspace. Use when you receive channel messages or need to report progress on tasks.
agentrq
Lead multiple agents to accomplish big tasks with specialized workspaces/agents by assigning tasks to specialized agents.
himalaya
Manage email accounts and mailboxes through the local Himalaya CLI. Use for reading mail, searching folders, flagging messages, moving or deleting messages, downloading attachments, composing or sending messages/templates, and diagnosing Himalaya email account configuration once the skill runtime is enabled.