Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/drippy-passport968/agent-supervision-skillsnpx agentmods add skills/drippy-passport968/agent-supervision-skills/claude-supervisionWrote 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.
[](https://agentmods.dev/skills/drippy-passport968/agent-supervision-skills/claude-supervision)<a href="https://agentmods.dev/skills/drippy-passport968/agent-supervision-skills/claude-supervision"><img src="https://agentmods.dev/badge/skills/drippy-passport968/agent-supervision-skills/claude-supervision/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.
<a href="https://agentmods.dev/skills/drippy-passport968/agent-supervision-skills/claude-supervision"><img src="https://agentmods.dev/badge/skills/drippy-passport968/agent-supervision-skills/claude-supervision.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00117 | $0.07077 |
| Opus 5 | $0.00059 | $0.03538 |
| Sonnet 5 | $0.00023 | $0.01415 |
| Haiku 4.5 | $0.00012 | $0.00708 |
Grade A, and why
claude-supervision scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- claude-supervision — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 491 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Supervision
Hand work to the local claude CLI (Anthropic's Claude Code) and supervise the result — read what Claude actually did, inspect artifacts, verify claims, only then answer the user.
Supervision, not blind delegation.
This is the Claude-Code analog of kimi-supervision and codex-supervision. Use it when you (Codex, another Claude session, a CI script, etc.) want to delegate to Claude Code non-interactively and need the answer + artifacts in a structured place.
Requirements
- PowerShell 7+ (
pwsh.exe).claude-setup.ps1refuses to markready=trueon PS 5.1. - Claude Code CLI (
claudefrom@anthropic-ai/claude-code). Install:npm install -g @anthropic-ai/claude-code. - Authentication:
claude auth login(interactive once), OR$env:ANTHROPIC_API_KEY/$env:ANTHROPIC_AUTH_TOKEN. Verified byclaude auth status(JSON output, exit 0=in / 1=out).
What this skill provides
Scripts under scripts/:
common.ps1— claude path resolution, env hygiene, async I/O, timeout, artifact capture, secret-redacted CLI arg recording, native session JSONL recovery (reads~/.claude/projects/<encoded-cwd>/<uuid>.jsonlwhen stdout is unexpectedly empty)claude-setup.ps1—claude auth statusJSON probe + PS 7+ + writable state dirclaude-task.ps1— delegate a task viaclaude --print(foreground, blocking)claude-review.ps1— multi-agent cloud-hosted review viaclaude ultrareviewclaude-bg.ps1— manage background sessions:--bg/agents/logs/stop/respawn/rm/daemon statusclaude-list-sessions.ps1— inspect this wrapper's own session artifacts
These scripts:
- prefer the native
claude.exeat$USERPROFILE\.local\bin\(no .cmd shim chain → no Windows stdio race like codex) - read/write UTF-8 throughout; set
Console.OutputEncodingto UTF-8 - pass the prompt via stdin (no argv length limits, no quoting hell on multi-line/unicode text)
- async stdout/stderr reads with
ReadToEndAsync(no pipe-buffer deadlock) -TimeoutSecwith hard kill (Process.Kill($true)withKill()fallback for older runtimes) andclassification='timeout'- always write
last-prompt.txt,last-response.txt,stderr.log,session.jsonto the session dir - session ID format
YYYYMMDD-HHmmss-fff-<PID>-<rand>-<mode>(no same-millisecond collisions) - redact secrets in
--settings/--mcp-config/--agents/--json-schema/--*-system-promptinline JSON before serializing to session.json - truncate long inline JSON args in
session.jsonfor readability
What ships with it
6 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.
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.
- 12d ago First seen · 491 lines · 117 tokens per session scan A bf7063c21d5c
claude-supervision is a skill published in the GitHub repository drippy-passport968/agent-supervision-skills (3 stars, last pushed today), licensed MIT. It adds 117 tokens to every session and 7,077 once invoked, about $0.0006 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.
Other skills, from other repositories
security-review
Complete a security review of the pending changes on the current branch.
code-review
Review the current diff, or a PR number/branch/path target, for correctness bugs and reuse/simplification/efficiency cleanups at the given effort level (low/medium: fewer, high-confidence findings; high→max: broader coverage, may include uncertain findings; ultra: deep multi-agent review in the cloud); with no level…
contribute-to-eliza
Finish and prove a scoped elizaOS GitHub issue, or independently review and repair an open elizaOS pull request. Use when contributing compute to elizaOS by selecting unclaimed work, implementing or reviewing changes, adding real tests and evidence, validating artifacts, or preparing a contribution for maintainer…
simplify
Review the changed code for reuse, simplification, efficiency, and altitude cleanups, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that.
ha-code-review
Hope-native review of uncommitted, staged, commit, branch, or PR changes: discover concrete regressions, independently verify candidates, and report actionable findings first without speculative noise.
factory-rereview
Re-review a pull request after a push — reconcile the previous review against the new commits, look for new defects the push introduced, then a fresh pass over the whole PR, and finish with a verdict on the PR.