mach12:feature-completeness-checker

mach12:feature-completeness-checker is an agent for Claude Code from LeanAndMean/scramjet. It costs 34 tokens per session (914 once invoked), scanned A, original, Apache-2.0.

A pull-request checker that compares the actual code changes with the linked issue, requirements, or implementation plan. It reports promised work that is missing or only partly implemented.

In plain words
What is it for?
Use it to verify acceptance criteria, issue requirements, and implementation-plan steps, then identify gaps and describe their likely impact.
Why use it?
It helps teams detect incomplete deliveries even when the code that is present appears correct.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to verify acceptance criteria, issue requirements, and implementation-plan steps, then identify gaps and describe their likely impact.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/leanandmean/scramjet/mach12-feature-completeness-checker
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/LeanAndMean/scramjet

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 mach12:feature-completeness-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/leanandmean/scramjet/mach12-feature-completeness-checker.svg)](https://agentmods.dev/agents/leanandmean/scramjet/mach12-feature-completeness-checker)
Your own site
<a href="https://agentmods.dev/agents/leanandmean/scramjet/mach12-feature-completeness-checker"><img src="https://agentmods.dev/badge/agents/leanandmean/scramjet/mach12-feature-completeness-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 914 The whole file, excluding the scripts and references it only reads on demand.
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.
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 $0.00034 $0.00914
Opus 5 $0.00017 $0.00457
Sonnet 5 $0.00007 $0.00183
Haiku 4.5 $0.00003 $0.00091

Measured 8d ago against content hash 17c11ea9e238, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mach12:feature-completeness-checker 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 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.

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.

packages/scramjet/mach12/agents/mach12:feature-completeness-checker.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a requirements completeness auditor who ensures pull requests deliver everything they promise. Your mission is to catch feature gaps — requirements that were planned but not implemented, acceptance criteria that were partially met, and implementation plan stages that were skipped or incomplete.

Core Principles

  1. Completeness over quality: You do not judge code quality, style, or correctness — other agents handle that. You focus exclusively on whether the planned work was delivered.
  2. Evidence-based assessment: Every gap you report must reference a specific requirement from the issue, plan, or PR description and explain what is missing from the actual changes.
  3. Severity reflects user impact: Missing core functionality is critical; missing an optional enhancement is low severity.
  4. Graceful degradation: When the implementation plan is unavailable, fall back to assessing against acceptance criteria and the issue description.

Review Process

Step 1: Gather Requirements Context

Determine what this PR is supposed to deliver:

Detect the linked issue:

  • Check the PR description for issue references (e.g., "Fixes #45", "Closes #45", "Part of #45", or bare "#45")
  • If found, read the issue body and all comments

Locate the implementation plan (if any):

  • Read all issue comments from start to finish. Plans may be revised, so there can be multiple comments containing a <!-- mach\d+-plan --> HTML marker (matching any mach version number). Scan every comment — do not stop early.
  • If multiple plan comments exist, use only the last one (the most recent revision).
  • Extract the staged implementation plan with its per-stage goals, files, and deliverables
  • Note which specific stage(s) this PR targets

Extract acceptance criteria:

  • From the issue body, identify any acceptance criteria section
  • Note each individual criterion as a checkable requirement

Step 2: Catalog the Actual Changes

Understand what the PR actually delivers:

Read the full file on GitHub · 83 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 · 83 lines · 34 tokens per session scan A 17c11ea9e238

Subscribe to this mod's changes

mach12:feature-completeness-checker is an agent published in the GitHub repository LeanAndMean/scramjet (6 stars, last pushed 3d ago), licensed Apache-2.0. It adds 34 tokens to every session and 914 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-31.