Claude-Pipeline: Command for Claude Code

.claude/commands/pmatch.md

pmatch is a command for Claude Code from TheAstrelo/Claude-Pipeline. It costs 0 tokens per session (564 once invoked), scanned B, original, MIT.

A command that compares a design document with an implementation plan to find missing requirements, unnecessary work, contradictions, or incomplete steps. A design document describes the intended result, while a plan lists how to build it.

In plain words
What is it for?
Use it after design and planning to create a drift report and determine whether the plan is aligned, needs revision, or cannot be checked.
Why use it?
It catches plan drift before coding begins, when changes are easier to make. It requires an active session containing both the design and plan.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is TheAstrelo/Claude-Pipeline's own configuration. It tells Claude Code how to work on Claude-Pipeline itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Claude-Pipeline configures →

Reuse

Borrowing it

Nothing to install: this file belongs to TheAstrelo/Claude-Pipeline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/TheAstrelo/Claude-Pipeline/main/.claude/commands/pmatch.md
Clone the repo
git clone --depth 1 https://github.com/TheAstrelo/Claude-Pipeline

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 pmatch

README.md
[![agentmods](https://agentmods.dev/badge/commands/theastrelo/claude-pipeline/pmatch.svg)](https://agentmods.dev/commands/theastrelo/claude-pipeline/pmatch)
Your own site
<a href="https://agentmods.dev/commands/theastrelo/claude-pipeline/pmatch"><img src="https://agentmods.dev/badge/commands/theastrelo/claude-pipeline/pmatch.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 564 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00000 $0.00564
Opus 5 $0.00000 $0.00282
Sonnet 5 $0.00000 $0.00113
Haiku 4.5 $0.00000 $0.00056

Measured 8d ago against content hash 01bde36ef964, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

pmatch scanned grade B 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 8d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

SESSION_DIR=$(cat .claude/artifacts/current.txt 2>/dev/null)
.claude/commands/pmatch.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verify plan-design alignment before build.


Prerequisites

Check that both design and plan exist:

SESSION_DIR=$(cat .claude/artifacts/current.txt 2>/dev/null)
if [ -z "$SESSION_DIR" ]; then
  echo "ERROR: No active session. Run /arm first."
  exit 1
fi
if [ ! -f "$SESSION_DIR/design.md" ]; then
  echo "ERROR: No design.md found. Run /design first."
  exit 1
fi
if [ ! -f "$SESSION_DIR/plan.md" ]; then
  echo "ERROR: No plan.md found. Run /plan first."
  exit 1
fi

Drift Detection

Use the drift-detector agent.

Input:

  • Read design.md from the current session directory
  • Read plan.md from the current session directory

Process:

  1. Extract all design requirements:

    • Components to create
    • APIs to implement
    • Database changes
    • Behavior specifications
    • Error handling requirements
  2. Map each requirement to plan step(s)

  3. Check for drift types:

    • Missing Coverage: Design requirement not in plan
    • Scope Creep: Plan step not justified by design
    • Contradictions: Plan conflicts with design
    • Incomplete Steps: Plan step missing required detail
  4. Output drift-report.md


Verdict Rules

ALIGNED if:

  • All design requirements covered
  • No unjustified scope creep
  • No contradictions
  • All steps complete

DRIFT_DETECTED if:

  • Any requirement uncovered
  • Unjustified scope creep
  • Any contradiction
  • Critical incomplete step

Output

After detection, report:

## Drift Detection Complete

**Session:** {session-directory}
**Verdict:** [ALIGNED | DRIFT_DETECTED]

### Coverage
- Design requirements: [N]
- Covered by plan: [N]
- Missing: [N]

### Issues Found
[List any drift issues]

### Next Step
[If ALIGNED] Run `/build` to implement the plan.
[If DRIFT_DETECTED] Fix the drift issues:
- Missing coverage: Update /plan
- Scope creep: Justify or remove
- Contradictions: Resolve which is correct

User Override

If drift is detected but the user wants to proceed anyway:

Read the full file on GitHub · 115 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. 8d ago First seen · 115 lines · 0 tokens per session scan B 01bde36ef964

Subscribe to this mod's changes

pmatch is a command published in the GitHub repository TheAstrelo/Claude-Pipeline (44 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 564 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.