wise-revise

wise-revise is a skill for Claude Code from e1024kb/wise-claude. It costs 255 tokens per session (2,719 once invoked), scanned B, original, MIT.

A read-only code-improvement planner that examines a folder, component, or project and writes a detailed implementation plan.

In plain words
What is it for?
Use it to investigate worthwhile improvements and save executable plans under docs/plans/ for later implementation or workflow automation.
Why use it?
It turns broad requests such as improving an API or paying down technical debt into specific work without changing source files.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

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 investigate worthwhile improvements and save executable plans under docs/plans/ for later implementation or workflow automation.

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-revise

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/e1024kb/wise-claude/wise-revise"><img src="https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-revise.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 255 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,719 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00255 $0.02719
Opus 5 $0.00128 $0.01359
Sonnet 5 $0.00051 $0.00544
Haiku 4.5 $0.00026 $0.00272

Measured 9d ago against content hash 73009f72f2d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

wise-revise scanned grade B 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 9d 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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

that tries to redirect the agent ("ignore previous instructions") is

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

plugins/wise/skills/wise-revise/SKILL.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/wise-revise — investigate a scope, write executable improvement plans

Why this skill exists

wise has reactive quality tiers (the per-commit simplify pass, the heavyweight branch code-review gate) and autonomous ticket→PR pipelines, but nothing proactive — no "study this and tell me what is worth improving, then spec it" step. /wise-revise is that planner.

It splits the work the way wise tiers models: the expensive brain (the Lead Architect, wise:architect) understands the code, judges what matters, and writes the spec; execution is delegated to you. The plan is the product. The skill investigates read-only and writes only under docs/plans/ — it never edits source, never runs a mutating command, and never executes a plan. Because each plan is authored in wise's existing PLAN-*.md schema, you can later drive it to a merged PR end to end with /wise-workflow-run impl-plan-auto docs/plans/<NNN>-<slug>.md (re-plan → implement → review → PR → watch → merge), run it verbatim on this branch with /wise-implement-plan-auto docs/plans/<NNN>-<slug>.md, file the finding as a ticket and let the ticket-auto workflow build it from the ticket, or hand it to any engineer — your call, not this skill's. (impl-plan-auto re-plans from this file against current HEAD; ticket-auto starts from a ticket; /wise-implement-plan-auto runs this plan as written.)

Invocation

/wise-revise <what to improve / which scope>
/wise:wise-revise <…>                # canonical namespaced form

The argument is a single free-form prompt that carries both:

  • the scope — a path or glob (src/auth, packages/api/**), a component / module name, or nothing / "the whole project" → the repo root; and
  • the intent — what to improve ("performance", "tech debt", "test coverage", "security", "general cleanup", or an open "improve this").

An optional quick or deep word anywhere in the prompt nudges depth (default: scale depth to the scope). Examples:

Read the full file on GitHub · 239 lines

Files

What ships with it

2 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.

  1. 9d ago First seen · 239 lines · 255 tokens per session scan B 73009f72f2d5

Subscribe to this mod's changes

wise-revise is a skill published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed yesterday), licensed MIT. It adds 255 tokens to every session and 2,719 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it B with 1 finding (instruction-override phrasing). 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