Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Adjudicate

ASecurity

Resolve every recommendation, CRUX, and open question from the latest Forged critique, write accepted decisions into the ledger-native work-item fields, and make the record ready only when its execution contract is complete. Use after /forged:critique or when the operator invokes /forged:adjudicate.

2 stars
0 votes
0 copies
0 views
Added 9/3/2026
developmentbashgit

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add tcashel/forge --skill adjudicate --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Adjudicate?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Adjudicate
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tcashel-adjudicate/badge)](https://www.skillsdirectory.com/skills/tcashel-adjudicate)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: adjudicate
description: "Resolve every recommendation, CRUX, and open question from the latest Forged critique, write accepted decisions into the ledger-native work-item fields, and make the record ready only when its execution contract is complete. Use after /forged:critique or when the operator invokes /forged:adjudicate."
---

# /forged:adjudicate

Position: `forged explain --id "$WORK_ID"` must report lifecycle stage `critiqued`.
Next: `forged next --repo "$TARGET_REPO"` reports dispatch only after atomic adjudication.

Boundary: the lead owns evidence checks, CRUX choices, and operator dialogue.
The ledger performs the guarded field, note, and status transition as one
operation; execution still requires a later explicit handoff.

## Load the critique

```bash
forged explain --id "$WORK_ID"
forged work note list --id "$WORK_ID" --kind recommendation --limit 500
```

Require lifecycle stage `critiqued`, then load the exact recommendation row
whose `noteId` is named by `lifecycle.basis.noteIds`; do not substitute another
recommendation. Decode its `bodyJson`. If the named row is absent from this
bounded result, stop instead of guessing or scanning another source.

## Resolve every finding

Use the newest `forged.spec-recommendations/1` note named by the lifecycle
projection. Verify its work id and repository against the current record; a
missing, stale, malformed, or mismatched recommendation returns to critique.

1. Verify each recommendation against current repository evidence; accept,
   adapt, or reject it with a reason.
2. Present one unresolved CRUX at a time with facts, bounded options,
   consequences, and a recommended choice. Capture operator decisions when
   product scope or external authority changes.
3. Resolve open questions and reconcile every native field and dependency.
4. Fold accepted outcomes into normative fields; retain rejection reasons.

There is no “defer to implementation” disposition. A later-wave assumption
remains an explicit hold.

## Commit the adjudication atomically

Prepare complete field bodies and one raw `forged.adjudication/1` payload
outside the repository. Each referenced file must be readable, nonempty, and
UTF-8. The payload names the recommendation note and covers every
recommendation and CRUX:

```json
{
  "schema": "forged.adjudication/1",
  "workItem": "<ore-id>",
  "critiquedRevision": 4,
  "recommendationNoteId": "<note-id>",
  "resultingRevision": 5,
  "dispositions": [
    {"ref": {"noteId": "<note-id>", "index": 0}, "disposition": "accept", "reason": "<evidence>"},
    {"ref": {"noteId": "<note-id>", "cruxId": "CRUX-1"}, "disposition": "accept", "reason": "<choice basis>"}
  ],
  "cruxes": [{"id": "CRUX-1", "choice": "<choice>", "rationale": "<reason>"}],
  "adjudicatedAt": "<ISO-8601 UTC>",
  "actor": "<operator or lead>"
}
```

`resultingRevision` equals the observed revision when fields do not change and
the next revision when any field changes.

```bash
forged work adjudicate --id "$WORK_ID" \
  --expected-revision "$OBSERVED_REVISION" --title "$TITLE" \
  --description-file "$DESCRIPTION_PATH" --design-file "$DESIGN_PATH" \
  --acceptance-file "$ACCEPTANCE_PATH" --notes-file "$NOTES_PATH" \
  --dispositions-file "$DISPOSITIONS_PATH"
forged explain --id "$WORK_ID"
forged next --repo "$TARGET_REPO"
```

Stop on a moved revision, reconcile the newer record and evidence, then make
one fresh operation. Verify the resulting lifecycle, revision, note id,
repository, fields, and graph. Report each disposition and any remaining hold.

## Never

- Do not conceal an unresolved question or make an incomplete stub ready.
- Do not create a parallel spec, rerun critics to seek unanimity, or execute.
- Do not change GitHub, install software, or edit the target repository.

Attribution

tcasheltcashel
View sourceMore from tcashel →
SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Know which skills are safe — weekly.

Best new skills + every skill we flagged as malicious. From the team that scanned 103,619.

Join free

Related Skills

Browser Extension Developer

Use this skill when developing or maintaining browser extension code in the `browser/` directory, including Chrome/Firefox/Edge compatibility, content scripts, background scripts, or i18n updates.

281612 votes

Seo Optimizer

SEO optimization with keyword analysis, readability assessment, technical validation, content quality. Use for search rankings, blog posts, content audits, or encountering keyword density, readability scores, meta tags, schema markup errors.

2132 votes

Google Official Seo Guide

Official Google SEO guide covering search optimization, best practices, Search Console, crawling, indexing, and improving website search visibility based on official Google documentation

1862 votes

Tanstack Start

Build a full-stack TanStack Start app on Cloudflare Workers from scratch — SSR, file-based routing, server functions, D1+Drizzle, better-auth, Tailwind v4+shadcn/ui. Use whenever the user mentions TanStack Start, asks to scaffold a full-stack Cloudflare app with SSR, wants an SSR dashboard, or asks for a React 19 + Cloudflare Workers app with file-based routing and server functions — even if they don't name TanStack Start specifically. No template repo — Claude generates every file fresh per ...

9881 votes

Pentest

PTES-aligned adversarial security audit for backend, frontend, and mobile applications. Produces a CVSS-scored Hacker Report with verified PoCs and phased remediation.

5491 votes
View all in development →