A workflow for turning a correction or project-specific discovery into a lasting instruction for the right project or plugin location. It can also remove duplicate entries from feedback notes after confirmation.

Use it to record durable project guidance, decide where that guidance belongs, and clean up duplicate feedback entries.

Important corrections can be lost between sessions or stored in the wrong kind of memory. This routes them to instructions, runbooks, or other project knowledge rather than treating personal style feedback as project rules.

do-learn — Skill for Claude Code by Jerry0022/dotclaude

Install

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.

Any agent

npx skills add Jerry0022/dotclaude --skill do-learn

Clone the repo

git clone --depth 1 https://github.com/Jerry0022/dotclaude

Made for: Claude Code.

Or install devops, the plugin that ships this one along with the rest of its 18 skills, 12 agents, 9 hooks, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jerry0022/dotclaude/do-learn/github.svg)](https://agentmods.dev/skills/jerry0022/dotclaude/do-learn)

Your own site

<a href="https://agentmods.dev/skills/jerry0022/dotclaude/do-learn"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/do-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jerry0022/dotclaude/do-learn"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/do-learn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 195 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,590 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00195	$0.03590
Opus 5.5	$0.00078	$0.01436
Sonnet 5.5	$0.00039	$0.00718
Haiku 4.5	$0.00019	$0.00359

Measured 11d ago against content hash 4e417f3424bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

do-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 11d 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.

plugins/devops/skills/do-learn/SKILL.md · 251 lines

How it starts

The opening of the file, as written. The whole thing — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learn — Capture a Project-Persistent Learning

Persist a correction so it survives across sessions. Personal style/tone feedback belongs in auto-memory and is handled elsewhere — this skill writes project- or plugin-specific rules.

Step 0 — Load extensions

Injected by the override loader ([skill-overrides] block); none shown → none exist.

Step 1 — Collect the learning

Text passed after /do-learn is the learning — with two shapes that need work before they are a rule:

A question or complaint ("warum ship nicht funktioniert", "warum hast du X übersehen", "fix das + learn"): the learning is the root cause, not the sentence. Diagnose first with evidence (logs, code, the transcript), fix what the prompt asked to fix, then state the rule the root cause implies.
Several learnings in one call (numbered lists, "zwei Themen", a paragraph per topic): split into atomic rules and run Step 2 for each. Rules that land in the same target repo go into one /auto-issue call (it takes several issues); local writes are grouped per file. Never let one learning's branch decide the others'.
One learning, two independent topics (a symptom report naming two defects that do not share a fix, e.g. "login window and console pop-ups"): split it like several learnings — each topic gets its own rule and, in branch B / D, its own issue (Split rule in {PLUGIN_ROOT}/skills/auto-issue/deep-knowledge/issue-rules.md). Never hand /auto-issue one issue that bundles them.

Otherwise mine the conversation before asking — a bare invocation almost always follows a moment where Claude did something the user did not expect. Walk the user's prompts backwards, newest first, and stop at the first one that carries a surprise: the user corrects a result, questions why something happened, states an expectation that was not met, or reverses something Claude did ("nein, …", "warum hast du …", "das sollte …", "ich wollte eigentlich …", "not what I asked", "that's wrong"). Most of the time it is the prompt immediately before /do-learn; go further back only while the newer prompts are neutral (plain task requests, acknowledgements, "ok", "weiter"). Never skip past a surprise to a different, older one.

Read the full file on GitHub · 251 lines

Files

What ships with it

3 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.

Changes

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.

11d ago Changed · +2 lines 4e417f3424bc
15d ago Changed · +6 lines 891b51c81129
16d ago Changed · -5 lines b7b1318ed711
1mo ago Changed · -11 lines 43a6995bfef7
1mo ago First seen · 259 lines · 195 tokens per session scan A d87bdd0cf0cb

Subscribe to this mod's changes

do-learn is a skill published in the GitHub repository Jerry0022/dotclaude (6 stars, last pushed 11d ago), licensed MIT. It adds 195 tokens to every session and 3,590 once invoked, about $0.0008 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 2026-09-24.

Memory and context

do-learn next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
do-learnJerry0022/dotclaude	Skill	6	11d ago	MIT	A	195	Claude Code
knowledge-ingestopenclaw/openclaw	Skill	394k	yesterday	MIT	A	80	Claude Code, Codex
mem0-oss-to-platformmem0ai/mem0	Skill	68k	2d ago	Apache-2.0	A	217	Claude Code, Codex
forgetasgeirtj/system_prompts_leaks	Skill	71k	2d ago	CC0-1.0	A	74	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	yesterday	MIT	A	184	Claude Code
memoryopensquilla/opensquilla	Skill	7.1k	6d ago	Apache-2.0	A	44	Claude Code, Codex
ha-data-storesshiwenwen/hope-agent	Skill	1.9k	yesterday	MIT	A	115	Claude Code, Codex