Vouch

Partner, reviewed

**Stage. Verify. Promote.**

Plugin · by hadifrt20 · runs in Claude Code, Cowork, claude.ai · 7 skills, 3 agents · listed 2026-05-10

Claude Code

claude plugin install vouch

Source

Skills (7)

Skill vouch-init

Scaffold a new vouch pipeline project — interview-style. Produces pipeline.md describing stages, optional budget.json wallet, optional checklist.md witness template, and an initial state file.

Any agent
```
npx skills add hadifrt20/vouch --skill vouch-init
```
Skill vouch-promote

Tournament-gate ANY change to a Claude Code artifact. Candidates can be prompts, SKILL.md files, subagent definitions, MCP/settings configs, hooks, agent flows, full pipeline.md files — anything…

Any agent
```
npx skills add hadifrt20/vouch --skill vouch-promote
```
Skill vouch-resume

Resume a failed or interrupted vouch run. Re-runs phases that are in failed/skipped state without disturbing completed phases.

Any agent
```
npx skills add hadifrt20/vouch --skill vouch-resume
```
Skill vouch-run

Execute a vouch pipeline by running stages sequentially, debiting the budget per stage, spawning the vouch-stage subagent for the work, and optionally calling vouch-adversary on any Claim objects in…

Any agent
```
npx skills add hadifrt20/vouch --skill vouch-run
```
Skill vouch-status

Print a compact status dashboard for a vouch project — current run progress, phase breakdown, last-N runs, budget balance, latest adversary survival rate. Useful at any point during or after a run.

Any agent
```
npx skills add hadifrt20/vouch --skill vouch-status
```
Skill vouch-verify

Run the vouch adversary against a list of Claims and write verified verdicts. Use this standalone (without /vouch-run) when you already have a JSON file of claims and want survival scores attached.

Any agent
```
npx skills add hadifrt20/vouch --skill vouch-verify
```
Skill vouch-witness

Evaluate a target document against a markdown checklist. Produces a witness report with per-section pass/fail, severity-weighted score, and follow-up questions sourced from the markdown — not from…

Any agent
```
npx skills add hadifrt20/vouch --skill vouch-witness
```

Agents (3)

Agent vouch-adversary

Verify a list of claim objects against one or more verification modes (source / contradiction / cross_reference / temporal).
Agent vouch-judge

Compare two candidates under a named judging criterion and return a winner verdict. Candidates can be prompts, SKILL.md files, subagent definitions, settings/MCP configs, hooks, pipeline.md files…
Agent vouch-stage

Execute one stage of a vouch pipeline. Reads the stage description from pipeline.md, runs whatever the stage requires (LLM call, tool invocation, computation), and writes the result as JSON to the…

From Anthropic's public plugin directory, read on 2026-10-15. Find a skill by task.