mine-claude-md

mine-claude-md is a skill for Claude Code from ragnar-pwninskjold/tech-snacks. It costs 91 tokens per session (972 once invoked), scanned A, original, MIT.

A review workflow that finds useful, non-obvious lessons in recent Claude Code sessions and turns them into proposed additions for a CLAUDE.md project-instructions file.

In plain words
What is it for?
Use it to review multi-file coding sessions, check possible documentation candidates, and produce additions you can paste into CLAUDE.md.
Why use it?
It helps recover important patterns and mistakes from past work without silently adding guesses or changing the file itself.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions Claude Code.

Part of the tech-snacks plugin — 8 skills shipped together

Good fit Use it to review multi-file coding sessions, check possible documentation candidates, and produce additions you can paste into CLAUDE.md.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ragnar-pwninskjold/tech-snacks/mine-claude-md
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 ragnar-pwninskjold/tech-snacks --skill mine-claude-md
Clone the repo
git clone --depth 1 https://github.com/ragnar-pwninskjold/tech-snacks

Made for: Claude Code.

Or install tech-snacks, the plugin that ships this one along with the rest of its 8 skills.

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.

agentmods badge for mine-claude-md

README.md
[![agentmods](https://agentmods.dev/badge/skills/ragnar-pwninskjold/tech-snacks/mine-claude-md/github.svg)](https://agentmods.dev/skills/ragnar-pwninskjold/tech-snacks/mine-claude-md)
Your own site
<a href="https://agentmods.dev/skills/ragnar-pwninskjold/tech-snacks/mine-claude-md"><img src="https://agentmods.dev/badge/skills/ragnar-pwninskjold/tech-snacks/mine-claude-md/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.

agentmods 80×15 button for mine-claude-md

Your own site · 80×15
<a href="https://agentmods.dev/skills/ragnar-pwninskjold/tech-snacks/mine-claude-md"><img src="https://agentmods.dev/badge/skills/ragnar-pwninskjold/tech-snacks/mine-claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 972 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00091 $0.00972
Opus 5 $0.00046 $0.00486
Sonnet 5 $0.00018 $0.00194
Haiku 4.5 $0.00009 $0.00097

Measured 13d ago against content hash a0c219dc0339, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mine-claude-md 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 13d 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/tech-snacks/skills/mine-claude-md/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mine-claude-md

Harvest non-obvious knowledge out of a project's recent Claude Code sessions and turn it into proposed CLAUDE.md additions — without inventing anything. This runs a bundled dynamic workflow that mines candidates in parallel, has independent skeptics adversarially challenge each one (reject-by-default), loops until the well runs dry, and synthesizes the survivors into a paste-ready report. It only proposes — it never edits your CLAUDE.md.

Requirements (check first)

This skill drives Claude Code's dynamic workflows feature. Before running, confirm:

  • Claude Code v2.1.154+ and a paid plan (Pro/Max/Team/Enterprise) or API access.
  • Workflows are enabled (/config → Dynamic workflows, or disableWorkflows not set, and CLAUDE_CODE_DISABLE_WORKFLOWS unset).

If workflows are disabled, the Workflow tool call below will fail. If it does, tell the user to enable Dynamic workflows in /config and re-run — do not fall back to doing the mining inline (the whole point is the parallel adversarial-verification harness).

Resolve the bundled workflow path

The orchestration script ships inside this plugin. Resolve its absolute path now — this works whether the plugin is installed at the personal, project, or plugin level, and regardless of the current working directory:

echo "${CLAUDE_SKILL_DIR}/../../workflows/mine-claude-md-from-sessions.workflow.js"

Use the path printed above as the scriptPath argument. Do not retype or guess it.

Gather inputs

Determine the workflow args before launching:

  • projectPath (required): the absolute path to the repo to mine. Default to the current project root (${CLAUDE_PROJECT_DIR} or the cwd) unless the user named a different repo.
  • sessionCount (optional, default 20): how many recent sessions to read.
  • maxRounds (optional, default 6): safety cap on mining rounds.
  • dryRounds (optional, default 2): consecutive empty rounds that mean "done".
  • miners (optional): miners per round; auto-scales 2–4 from session count if omitted.

Read the full file on GitHub · 79 lines

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.

  1. 13d ago First seen · 79 lines · 91 tokens per session scan A a0c219dc0339

Subscribe to this mod's changes

mine-claude-md is a skill published in the GitHub repository ragnar-pwninskjold/tech-snacks (132 stars, last pushed 25d ago), licensed MIT. It adds 91 tokens to every session and 972 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens