wise-insights-refine

wise-insights-refine is a skill for Claude Code from e1024kb/wise-claude. It costs 173 tokens per session (1,840 once invoked), scanned A, original, MIT.

A review tool for learned skills that finds overlapping instructions and proposes combining them into fewer skills.

In plain words
What is it for?
Use it to inspect possible overlaps, preview a consolidation plan, approve merged skills, and safely back up and retire the originals.
Why use it?
It helps prevent a growing skill library from accumulating redundant or unnecessarily separate instructions while keeping retirements reversible.

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 inspect possible overlaps, preview a consolidation plan, approve merged skills, and safely back up and retire the originals.

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-refine

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/e1024kb/wise-claude/wise-insights-refine"><img src="https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-insights-refine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 173 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,840 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00173 $0.01840
Opus 5 $0.00086 $0.00920
Sonnet 5 $0.00035 $0.00368
Haiku 4.5 $0.00017 $0.00184

Measured 10d ago against content hash 0f330fc7b834, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

wise-insights-refine 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 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.

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/wise/skills/wise-insights-refine/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/wise-insights-refine — consolidate learned skills

Why this skill exists

/wise-insights-mine drafts a new ~/.claude/skills/<name>/SKILL.md each time a recurring pattern crosses its threshold. Over time the library accumulates skills that overlap or compose. This command finds those overlaps and, with your per-group approval, merges redundant skills into one aggregated skill and retires the originals — reversibly (every retired skill is backed up first).

The deterministic work — enumerating skills, parsing the wise-insights marker, computing token overlap, and the destructive retire (backup → verify → delete) — lives in ${CLAUDE_PLUGIN_ROOT}/scripts/insights.py (stdlib-only). This skill runs it, judges which overlaps are genuinely the same task, synthesises the merged skill, and orchestrates the safe ordering. It never deletes files itself; retiring goes through the engine, which refuses to touch a skill that lacks the marker — so hand-written skills are structurally protected.

Arguments

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

  • --dry-run — show the consolidation plan (groups, proposed names, what would be retired and where it'd be backed up) and make NO writes or retires.
  • --min-jaccard <X> — overlap threshold (default 0.6). Lower surfaces looser overlaps; raise for only near-duplicates.
  • --include-external — also surface overlaps that involve hand-written (unmarked) skills. These are suggestion-only — the external skill is never retired; you're just told it overlaps.

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

Procedure

1. Guard on /wise-init, then enumerate + find overlaps

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 enumerate, do not bootstrap anything yourself.

Read the full file on GitHub · 145 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 · 145 lines · 173 tokens per session scan A 0f330fc7b834

Subscribe to this mod's changes

wise-insights-refine is a skill published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed today), licensed MIT. It adds 173 tokens to every session and 1,840 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 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