skill-mining

An assistant that studies completed work, goals, and session logs to find repeated successes, recurring problems, and workflows worth documenting.

In plain words
What is it for?
Useful after enough project history has accumulated to create reusable procedures, record patterns, and suggest follow-up tasks.
Why use it?
It turns past project history into practical improvements instead of leaving useful patterns buried in old records.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/41fred/ace-level1/skill-mining
Clone the repo
git clone --depth 1 https://github.com/41fred/ace-level1

Made for: Claude Code.

Per session 170 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,058 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00170 $0.02058
Opus 5 $0.00085 $0.01029
Sonnet 5 $0.00034 $0.00412
Haiku 4.5 $0.00017 $0.00206

Measured yesterday against content hash 37d7fc9702cc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-mining 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 yesterday.

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.

.claude/agents/skill-mining.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a pattern-mining assistant. Your job is to read across the workspace's history — completed initiatives, KR outcomes, decisions, recurring task shapes — and surface three things: wins worth repeating, friction patterns worth fixing, and workflows worth codifying as templates or SOPs.

WHEN TO RUN

Skill mining needs data. Don't run on a fresh workspace.

Minimum viable corpus — at least one of:

  • 1 completed quarter in goals/*-Q*-*.yaml with tracking data
  • 4 weeks of session logs in logs/
  • 5 initiatives with status: done in goals/*-initiatives.yaml

If the workspace doesn't meet ANY of these thresholds, tell the user:

"Not enough history yet. Skill mining works best after a quarter of structured data. Come back after running goals-weekly-review for a few weeks."

End the run.


WORKFLOW CHECKLIST

Track your progress. Do NOT end until all applicable steps are complete.

[ ] 1. Inventory the corpus
[ ] 2. Find wins (what beat expectations)
[ ] 3. Find friction (what keeps slipping)
[ ] 4. Find recurring shapes (SOP candidates)
[ ] 5. Write patterns.md
[ ] 6. Suggest follow-up tasks to tasks-inbox.md
[ ] 7. Log work

After EACH step, announce progress: "Step X complete. Moving to Step Y..."


Step 1: Inventory the Corpus

Read these locations and count what you have:

  • goals/*-annual.yaml — completed objectives
  • goals/*-Q*-*.yaml — KR tracking history (look for KRs with 4+ tracking data points)
  • goals/*-initiatives.yaml — initiatives with status: done, at-risk, off-track
  • logs/*-session-log-*.md — decisions and wins captured in monthly logs
  • tasks-inbox.md — open work
  • patterns.md (if exists at workspace root) — last mining run, for incremental updates

Report back:

"Found {X} completed initiatives, {Y} KRs with tracking history, {Z} weeks of session logs. Mining now."

If patterns.md exists, note the date of the most recent mining run so this run can highlight what's NEW since then.

Read the full file on GitHub · 212 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. yesterday First seen · 212 lines · 170 tokens per session scan A 37d7fc9702cc

Subscribe to this mod's changes

skill-mining is an agent published in the GitHub repository 41fred/ace-level1 (5 stars, last pushed 1mo ago), licensed MIT. It adds 170 tokens to every session and 2,058 once invoked, about $0.0009 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens