warrant

warrant is a plugin for Claude Code from fledgeling-co/fledgeling-plugins. Its manifest loads nothing; the 9 skills it bundles cost 880 tokens per session together, scanned A, original, MIT.

A rule-based system for deciding when a machine may close software-verification work and when evidence must revoke that authority.

In plain words
What is it for?
Use it to define signed authority, validate evidence, assess test sensitivity, record escapes, sample work, and calculate or revoke approval tiers.
Why use it?
It makes automated decisions traceable, limits them to approved defect classes and tiers, and sends disagreements or unsupported results for escalation.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

Good fit Use it to define signed authority, validate evidence, assess test sensitivity, record escapes, sample work, and calculate or revoke approval tiers.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add fledgeling-co/fledgeling-plugins
/plugin install warrant
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/fledgeling-co/fledgeling-plugins

Made for: Claude Code.

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 warrant

README.md
[![agentmods](https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/warrant/github.svg)](https://agentmods.dev/plugins/fledgeling-co/fledgeling-plugins/warrant)
Your own site
<a href="https://agentmods.dev/plugins/fledgeling-co/fledgeling-plugins/warrant"><img src="https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/warrant/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 warrant

Your own site · 80×15
<a href="https://agentmods.dev/plugins/fledgeling-co/fledgeling-plugins/warrant"><img src="https://agentmods.dev/badge/plugins/fledgeling-co/fledgeling-plugins/warrant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 9 skills cost 880 tokens a session between them.
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.
Security

Grade A, and why

warrant 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 1mo 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/warrant/.claude-plugin/plugin.json · 10 lines

What it actually says

{
  "name": "warrant",
  "description": "Remove the human from per-item software verification by granting a machine a written, tiered authority and revoking it automatically on evidence. Eight skills: charter (the signed warrant, the only human-signed artifact), oracle (source-to-render lineage, tick-and-tie, taxonomy validation — the deterministic plane, built first because the highest-consequence defect is a correctly rendered screen stating a figure no source supports), assay (mutation survival and cannot-fail patterns, because every downstream verdict inherits the suite's fault sensitivity), panel (one out-of-family grader plus orthogonal lens lanes plus an adjudicator that routes disagreement to arithmetic — deliberately not a jury, since nine judges from seven families supply about two effective votes), feedback (escapes become permanent regression cases; calibration from what got missed rather than from a reader study), lot (risk-limited acceptance of a queue, blind to the machine verdict), ratchet (computes earned tiers, applies revocations without asking, and is a plain script because the component deciding a model's authority should not be the model), and ledger (the hash-chained decision record an auditor reads instead of per-item signatures). Grounded in a 22-source panel across four research backends; every rule traces to a claim id in docs/deep-research/claims.json.",
  "version": "0.3.3",
  "author": {
    "name": "Fledgeling",
    "email": "[email protected]"
  }
}
Contents

What it installs

The manifest is a name and a version. 9 skills travel with it, and installing the plugin installs all of them — 880 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 1mo ago Changed 65614f12064e
  2. 1mo ago First seen · 10 lines scan A 0d1b95a72aa1

Subscribe to this mod's changes

warrant is a plugin published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-04.

Related

Other plugins, from other repositories

jira-pack

Issue-tracker pack: /jira-fix takes a ticket link of any type, verifies tracker access, classifies it as a defect or a change, reproduces the defect or writes a failing acceptance test for the change, routes the work to core executors, comments back with evidence and moves the ticket to the QA column. Opt-in; requires.

atretyak1985/swarmery · not measured

whetstone

Engineering-craft skills: red-green TDD, flaky-test audit, diagnosis, doubt review, grilling, merge-conflict resolution, research reports with grounded claims, HTML reports, skill linting and a column budget. Every gate among them carries a deterministic self-verify.

raisedadead/claude-code-plugins · not measured

es6kr

A collection of AI coding skills including TDD, commit management, dotfile sync, and more.

es6kr/skills · not measured

superpowers-deepseek-v4

Superpowers DeepSeek v4: composable agent skills for TDD, debugging, and collaboration. Independently maintained; not identical to obra/superpowers.

gylove1994/superpowers-deepseek-v4 · not measured

knowledge-virtuoso

15 knowledge skills — design patterns, refactoring, SOLID, debugging, clean architecture, testing, API design, security, scrum, performance, microservices, git workflow, CI/CD, accessibility, and database design.

krzysztofsurdy/code-virtuoso · not measured

safeword

AI coding agent workflows: BDD, auto-linting, quality reviews, debugging, and refactoring. Run safeword install in a project to enroll it.

ArcadeAI/safeword · not measured