wise-supervise

wise-supervise is a skill for Claude Code from e1024kb/wise-claude. It costs 189 tokens per session (1,477 once invoked), scanned A, original, MIT.

A supervisor loop for background coding agents, which are helpers working on tasks while you do not directly interact with each one.

In plain words
What is it for?
Use it to supervise a running agent team, check each member's status, nudge unfinished work, and escalate workers that remain stuck.
Why use it?
It detects agents that are idle, stuck, or drifting from their assigned goal and prompts or escalates them so the team does not stall.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: 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 supervise a running agent team, check each member's status, nudge unfinished work, and escalate workers that remain stuck.

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-supervise

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/e1024kb/wise-claude/wise-supervise"><img src="https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-supervise.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 189 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,477 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 $0.00189 $0.01477
Opus 5 $0.00095 $0.00739
Sonnet 5 $0.00038 $0.00295
Haiku 4.5 $0.00019 $0.00148

Measured 9d ago against content hash 9b01942aed3e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

wise-supervise 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 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.

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-supervise/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/wise-supervise — keep a running team of agents on task

Why this skill exists

Background teammates go idle after every turn and then wait forever unless someone messages them. So a workflow or ad-hoc team can stall not because a worker failed but because nobody told it what to do next — and today the only fix is the user typing "ping all your subagents, verify they're on track." This skill is that nudge, automated and repeatable: it probes the team, prods the stuck members, and escalates the ones that stay stuck.

It runs the shared supervisor routine in ${CLAUDE_PLUGIN_ROOT}/references/supervise-loop.md — read that first; this skill is the standalone, attach-to-any-team entry point for it. The workflow engine runs the same routine automatically for type: supervised-prompt steps.

Invocation

/wise-supervise                 # supervise the single active team (or ask which)
/wise-supervise ticket-pr-run   # supervise a named team
/wise:wise-supervise <team>     # canonical namespaced form

The positional, if present, is the team name. Anything else is ignored prose.

Procedure

1. Resolve the team

If a team name was given, use it. Otherwise read which teams exist and pick the single active one; if there is more than one, ask the user which to supervise (this is the one allowed prompt — the rest of the loop is decision-free unless a worker needs a human call). Read the team's members from its config:

Read ~/.claude/teams/<team-name>/config.json

The members[] array gives each teammate's name (always address members by name) and agentType. The team-lead entry is you / the conductor — supervise the worker members, not yourself.

2. Pick the detection mode

run.dir (and thus a workers/ heartbeat dir) is only known when a workflow run hands it to you — e.g. the conductor invoking the loop for a supervised-prompt step. A standalone /wise-supervise <team> typed by the user has no run context, so it has no run.dir and falls through to the legacy path. Concretely:

Read the full file on GitHub · 128 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. 9d ago First seen · 128 lines · 189 tokens per session scan A 9b01942aed3e

Subscribe to this mod's changes

wise-supervise is a skill published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed yesterday), licensed MIT. It adds 189 tokens to every session and 1,477 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