phase-enforcement

phase-enforcement is a skill for Claude Code from MadAppGang/claude-code. It costs 50 tokens per session (3,335 once invoked), scanned A, original, MIT.

A set of checks for an eight-phase feature-development process that verifies required work exists before each phase is marked complete.

In plain words
What is it for?
It helps enforce phase checkpoints, confirm required files exist, connect requirements to validation results, and track retries when work is blocked.
Why use it?
It prevents missing documentation or tests, skipped validation, unsupported completion claims, and unfinished work being treated as done.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

Part of the dev plugin — 47 skills, 12 commands, 14 agents shipped together

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.

agentmods
npx agentmods add skills/madappgang/claude-code/enforcement
Any agent
npx skills add MadAppGang/claude-code --skill enforcement
Clone the repo
git clone --depth 1 https://github.com/MadAppGang/claude-code

Made for: Claude Code.

Or install dev, the plugin that ships this one along with the rest of its 47 skills, 12 commands, 14 agents.

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 phase-enforcement

README.md
[![agentmods](https://agentmods.dev/badge/skills/madappgang/claude-code/enforcement.svg)](https://agentmods.dev/skills/madappgang/claude-code/enforcement)
Your own site
<a href="https://agentmods.dev/skills/madappgang/claude-code/enforcement"><img src="https://agentmods.dev/badge/skills/madappgang/claude-code/enforcement.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,335 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.03335
Opus 5 $0.00025 $0.01667
Sonnet 5 $0.00010 $0.00667
Haiku 4.5 $0.00005 $0.00333

Measured 2d ago against content hash 83bd85df8e3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

phase-enforcement scanned grade A with 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

2. Check if dev server is running: curl http://localhost:3000
plugins/dev/skills/enforcement/SKILL.md · 505 lines

How it starts

The opening of the file, as written. The whole thing — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase Completion Enforcement

Version: 1.0.0 Purpose: Mechanical enforcement of phase completion requirements for /dev:feature Status: Production Ready

Overview

This skill provides mechanical enforcement (not just prompt-based instructions) for the 8-phase feature development workflow. It prevents:

  1. Claiming completion without proof - Artifacts must exist
  2. Skipping documentation - Required files per phase
  3. Ignoring validation criteria - Phase 1 criteria must map to Phase 7 results
  4. Bypassing retry logic - Outer loop enforced with state tracking
  5. Shipping without tests - Phase 6 requires test files
  6. Faking completion when blocked - Graceful degradation with honest status
  7. Hiding actual results - Show-your-work requirement
  8. Missing automated checks - Checkpoint verification at boundaries

Enforcement Components

1. Phase Completion Validator

Script: scripts/phase-completion-validator.js

How it works:

  • Runs as PreToolUse hook on TaskUpdate
  • Detects phase from task subject (e.g., "Phase 3: Planning")
  • Checks required artifacts exist for that phase
  • Blocks completion if artifacts missing or empty

Required Artifacts per Phase:

Phase Required Artifacts Custom Checks
1 requirements.md, validation-criteria.md, iteration-config.json Config has required fields
3 architecture.md Plan reviews exist
4 implementation-log.md Git changes detected
5 reviews/code-review/consolidated.md Has PASS/FAIL verdict
6 tests/test-plan.md Test files created
7 validation/result.md Has PASS/FAIL status + evidence
8 report.md Phase 7 PASSED

Usage in orchestrator:

Before marking any phase complete:

1. Run checkpoint verification:
   ```bash
   ${PLUGIN_PATH}/scripts/checkpoint-verifier.sh phase{N} ${SESSION_PATH}
  1. If check passes, mark task complete:

    TaskUpdate(taskId: X, status: "completed")
    
  2. If check fails, DO NOT mark complete. Fix missing artifacts first.

Read the full file on GitHub · 505 lines

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. 2d ago First seen · 505 lines · 50 tokens per session scan A 83bd85df8e3b

Subscribe to this mod's changes

phase-enforcement is a skill published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 50 tokens to every session and 3,335 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

mpm-circuit-breaker-enforcement

Complete circuit breaker enforcement patterns with examples and remediation.

bobmatnyc/claude-mpm · 18 tokens

contract

Outcome-driven Cortex function development — declares a behavioral contract before generation begins, enforces evidence-tiered proof before $ship, and defends against the self-oracle evaluation failure mode.

Snowflake-Labs/cocoplus · 38 tokens

fable-thinking

Reasoning protocol distilled from Claude Fable 5.1. Makes any model reason like Fable — evidence-grounded claims, multi-hypothesis diagnosis, concrete simulation, adversarial self-review, calibrated outcome-first delivery. Its never-skipped Floor check catches simple-looking trick questions models answer confidently…

mrgoonie/fable-thinking · 198 tokens

scheduler-validation

Scheduler validator driven by ValidationHook — read-only static verification of scheduled jobs (schedule correctness, configuration, runtime context already collected by deterministic hook). Does not trigger test runs.

Datus-ai/Datus-agent · 37 tokens

evidence-calibration-review

Use when you want a per-claim evidence-tier audit on a text artifact before it ships — assign T1-T6 tiers to every load-bearing claim, surface calibration mismatches (high confidence on weak evidence, or honesty-theater under-claiming), and flag P11 (citation-as-decoration), P17 (pile-of-anecdotes-as-evidence), P54…

Avyayalaya/agent-council · 129 tokens

deep-deliberation

Runs a checkpoint-gated decision process for consequential, forward-looking design choices. Use only when the user explicitly invokes deep-deliberation to compare approaches, challenge assumptions, and reach an evidence-grounded recommendation before implementation. Use dissect instead to audit an existing system or…

afaraha8403/balakit · 60 tokens