wise-insights-mine

wise-insights-mine is a skill for Claude Code from e1024kb/wise-claude. It costs 168 tokens per session (2,279 once invoked), scanned C, original, MIT.

A skill that examines your own Claude Code session history to find task patterns that recur across separate sessions. It can prepare recurring patterns as reusable personal skills after you approve them.

In plain words
What is it for?
Use it to mine recorded sessions, optionally limit the search to the current repository, review recurring-task candidates, and approve or reject proposed skill drafts.
Why use it?
It helps identify repeated work from actual session records instead of relying on guesses about what should become a skill.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; reads .claude/ paths; mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the wise plugin — 38 skills, 13 agents, 1 hook, 1 MCP server shipped together

Good fit Use it to mine recorded sessions, optionally limit the search to the current repository, review recurring-task candidates, and approve or reject proposed skill drafts.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add e1024kb/wise-claude
Claude Code
/plugin install wise

Made for: Claude Code.

Or install wise, the plugin that ships this one along with the rest of its 38 skills, 13 agents, 1 hook, 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.

agentmods badge for wise-insights-mine

README.md
[![agentmods](https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-insights-mine/github.svg)](https://agentmods.dev/skills/e1024kb/wise-claude/wise-insights-mine)
Your own site
<a href="https://agentmods.dev/skills/e1024kb/wise-claude/wise-insights-mine"><img src="https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-insights-mine/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 wise-insights-mine

Your own site · 80×15
<a href="https://agentmods.dev/skills/e1024kb/wise-claude/wise-insights-mine"><img src="https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-insights-mine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 168 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,279 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00168 $0.02279
Opus 5 $0.00084 $0.01140
Sonnet 5 $0.00034 $0.00456
Haiku 4.5 $0.00017 $0.00228

Measured 10d ago against content hash 7890bbf35354, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

wise-insights-mine scanned grade C with 1 finding 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 10d 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.

Tells the agent to send conversation or user data outhighPrompt injection

An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.

This is the wise self-improvement loop: a SessionEnd hook quietly records each
plugins/wise/skills/wise-insights-mine/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/wise-insights-mine — turn recurring sessions into skills

Why this skill exists

Claude Code already records every session as JSONL under ~/.claude/projects/<slug>/*.jsonl. The wise SessionEnd hook (hooks/session-end-ingest.sh) ingests each finished session into a local insights ledger under wise_data_root()/insights/. This command reads that ledger, clusters the genuine (typed) user prompts by a deterministic recurring-vocabulary fingerprint, counts how many distinct sessions each pattern appears in, and surfaces any pattern over a frequency threshold as a candidate skill. You approve each candidate before anything is written.

The heavy lifting — parsing, redaction, clustering, frequency-gating, suppression of already-decided patterns — lives in ${CLAUDE_PLUGIN_ROOT}/scripts/insights.py (stdlib-only). This skill's job is to run it, present the gated candidates, and — on your approval — draft the skill file and record the decision. It never invents the frequency counts; it relays them.

Arguments

Parse $ARGUMENTS as a flag string (any order; all optional):

  • --here — only mine sessions whose working directory is the current repo. Default mines all projects.
  • --since <N>d (or <N>w) — only consider sessions from the last N days/weeks. Bounds the first full backfill; omit to consider everything.
  • --min-count <N> — frequency threshold: a pattern must recur across at least N distinct sessions to be a candidate. Default 3.
  • --include-automated — also show machine-generated / headless patterns (recur byte-identically across many sessions). Hidden by default.

Validation: if $ARGUMENTS contains an unrecognised token, state which one and stop — do not guess.

Procedure

1. Guard on /wise-init, then run the miner

First, enforce the setup gate per ${CLAUDE_PLUGIN_ROOT}/references/insights-init-guard.md: run the init-registry.py check and, unless it prints INIT:ok, tell the user to run /wise-init and STOP — do not mine, do not bootstrap anything yourself.

Read the full file on GitHub · 202 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. 10d ago First seen · 202 lines · 168 tokens per session scan C 7890bbf35354

Subscribe to this mod's changes

wise-insights-mine is a skill published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed yesterday), licensed MIT. It adds 168 tokens to every session and 2,279 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

docs-drift

Documentation-drift audit for this plugin monorepo. Audit either each scoped plugin's unreleased changelog claims or its latest shipped release from the previous reachable plugin-name--v tag, then verify that plugin READMEs, docs, CLAUDE.md or AGENTS.md files, and root documentation tell the truth for the matching…

gtapps/claude-code-hermit · 170 tokens

cco-tools

Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.

egorfedorov/claude-context-optimizer · 27 tokens

github-pr-creation

Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…

fvadicamo/dev-agent-skills · 75 tokens

test-run

Run plugin test suites in this monorepo and report a concise pass/fail summary. Optional plugin slug arg; without arg, runs all plugins under plugins/.

gtapps/claude-code-hermit · 35 tokens

design-system-reference

Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.

wigtn/wigtn-plugins · 43 tokens

magic-compact

Compact this Claude Code session.

aerovato/magic-compact · 10 tokens