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/qte77/claude-code-plugins/distilling-plan-learningsnpx skills add qte77/claude-code-plugins --skill distilling-plan-learningsgit clone --depth 1 https://github.com/qte77/claude-code-pluginsWrote 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/qte77/claude-code-plugins/distilling-plan-learnings)<a href="https://agentmods.dev/skills/qte77/claude-code-plugins/distilling-plan-learnings"><img src="https://agentmods.dev/badge/skills/qte77/claude-code-plugins/distilling-plan-learnings.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00910 |
| Opus 5 | $0.00000 | $0.00455 |
| Sonnet 5 | $0.00000 | $0.00182 |
| Haiku 4.5 | $0.00000 | $0.00091 |
Grade A, and why
distilling-plan-learnings 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 3d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan-to-Learnings Distiller
Target: $ARGUMENTS
Extracts structured learnings from Claude Code plan files. Distills decisions made, alternatives rejected, and patterns discovered into a persistent document that compounds project knowledge over time.
Arguments
| Position | Name | Required | Default | Description |
|---|---|---|---|---|
| 1 | time-range |
no | 7d |
E.g. 7d, 30d, this-week. Filter plans by modification time. |
| 2 | output-path |
no | docs/learnings/from-plans.md |
Where to write/append output. |
Examples:
/distilling-plan-learnings # Last 7 days → docs/learnings/from-plans.md
/distilling-plan-learnings 30d # Last 30 days
/distilling-plan-learnings 7d ./my-learnings.md # Custom output path
Data Source
~/.claude/
├── plans/*.md # Plan mode files (filtered by mtime)
When to Use
- After completing a plan or sprint — capture what was learned
- At week/sprint boundaries — accumulate decision history
- Before starting a new plan — review past decisions and patterns
Do Not Use
- For real-time plan editing (use plan mode directly)
- For cross-project synthesis (use
/synthesizing-cc-bigpicture) - For session-level context (use session-memory)
Workflow
-
Parse arguments — Apply defaults per Arguments table. Resolve output path. Create parent directories if needed.
-
Glob plans — Glob
~/.claude/plans/*.md. Filter by modification time against thetime-rangeargument. Sort by mtime descending (newest first). If no plans match, report "No plans found in time range" and stop. -
Read each plan — Read matching plan files sequentially. Extract content sections, noting plan title and date.
-
Extract learnings into three categories:
- Decisions made — Choices that were committed to. Look for: selected approaches, accepted trade-offs, finalized designs, chosen tools/patterns.
- Alternatives rejected — Options considered but not chosen. Look for: crossed-out items, "decided against", "considered but", trade-off discussions, pros/cons where one side won.
- Patterns discovered — Recurring themes or insights. Look for: repeated blockers, successful strategies, workflow improvements, reusable solutions.
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.
- 3d ago First seen · 117 lines · 0 tokens per session scan A ec78b2757735
distilling-plan-learnings is a skill published in the GitHub repository qte77/claude-code-plugins (2 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 910 tokens. 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
summarize-meeting
Summarize a meeting transcript into structured notes with date, participants, topic, key decisions, summary points, and action items. Use when processing meeting recordings, creating meeting notes, writing meeting minutes, or recapping discussions.
ppt-design-skill
Design, generate, review, and revise editable PowerPoint presentations through a rigorous brief-to-PNG workflow using the public pptx-designer Python library.
reflect-solution
Summarize WHAT WAS SHIPPED in a Claude Code session as a self-contained HTML slide deck — the elevator pitch (problem, solution, decisions, artifacts, verification, gaps), not a play-by-play of tool calls or debugging detours. Defaults to the current in-context session; optionally accepts a session ID or JSONL path.…
factcheck
Adversarial citation and claim audit for any document — "do these sources actually say what the text claims?" Takes a markdown file, URL, or pasted draft (including this repo's own pulse/verdict briefs), extracts every checkable claim, then fans out verifier sub-agents instructed to refute, not confirm: does the cited…
self-assess
Placement quiz that finds someone's real level in a subject and writes it to PROFILE.md. Scenario questions in small batches, never definitions, with neutral options that cannot be eliminated by tone, plus self-report checks that separate knowing a word from being able to act on it. Use when the user asks to measure…
lark-sheets
飞书电子表格:创建和操作电子表格。支持创建表格、管理工作表与行列结构(增删/合并/调整尺寸/隐藏/冻结)、读写单元格(值/公式/样式/批注/单元格图片)、查找替换、多操作原子批量更新,以及图表、透视表、条件格式、筛选器、迷你图、浮动图片等对象的创建与维护。当用户需要创建电子表格、管理工作表、批量读写或编辑数据、统计汇总与可视化、表格美化、公式计算(含 Excel 公式迁移)、金融/财务建模(DCF、三张表、预算、Sensitivity 等)等任务时使用。若用户是想按名称或关键词搜索云空间(云盘/云存储)里的表格文件,请改用 lark-drive 的 drive +search 先定位资源。当用户给出 doubao.com 的…