Skip to content
Back to skills

Consensus Loop

ASecurity

Guide for writing evidence packages for the consensus-loop watch file. Use when preparing code review submissions, structuring feedback evidence, or addressing audit rejections.

  • 15 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added May 26, 2026
code-quality

Works with

  • terminal

Security analysis

A100/100

Scanned May 27, 2026

npx -y skills add berrzebb/consensus-loop --skill consensus-loop --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Consensus Loop?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Consensus Loop
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/berrzebb-consensus-loop/badge)](https://www.skillsdirectory.com/skills/berrzebb-consensus-loop)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: consensus-loop:guide
description: "Guide for writing evidence packages for the consensus-loop watch file. Use when preparing code review submissions, structuring feedback evidence, or addressing audit rejections."
version: 1.0.0
---

# Consensus Loop — Evidence Package Guide

When submitting code changes for consensus review, write a properly structured evidence package in the watch file.

## Step 0: Read Config

Read `${CLAUDE_PLUGIN_ROOT}/config.json` first:
- `consensus.watch_file` → submission path
- `consensus.trigger_tag` / `agree_tag` / `pending_tag` → actual tag values
- `plugin.respond_file` → auditor verdict file
- `plugin.locale` → locale

## Step 1: Write Evidence

Follow the format defined in `${CLAUDE_PLUGIN_ROOT}/templates/references/${locale}/evidence-format.md`.

Required sections: **Claim**, **Changed Files**, **Test Command**, **Test Result**, **Residual Risk**.

Key rules:
- **Test Command** must be executable as-is — no glob patterns, use explicit file paths
- **Test Result** must be actual terminal output, not summaries
- **Claim** must match the actual code changes
- **Changed Files** paths must use backtick formatting
- Every changed file must pass eslint individually
- Use a single **Write** to the watch file (not sequential Edits)

## Step 2: Tag Lifecycle

```
[trigger_tag] → auditor reviews → [agree_tag] or [pending_tag]
                                        ↓
                                Fix issues, re-submit with [trigger_tag]
```

## Step 3: Addressing Rejections

When auditor returns `[pending_tag]`:

1. Read the rejection codes in the respond file (e.g., `test-gap`, `claim-drift`, `scope-mismatch`)
2. Fix each cited issue at the specific file:line locations
3. Update the evidence package with corrected claims, tests, and results
4. Keep the `[trigger_tag]` to trigger a new audit cycle

Full rejection code reference: `${CLAUDE_PLUGIN_ROOT}/templates/references/${locale}/rejection-codes.md`

Attribution

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

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.