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.
git clone --depth 1 https://github.com/LeanAndMean/scramjetWrote 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.
[](https://agentmods.dev/agents/leanandmean/scramjet/mach12-feature-completeness-checker)<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>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.
| Model | Per session | Once 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 |
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.
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
- 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.
- 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.
- Severity reflects user impact: Missing core functionality is critical; missing an optional enhancement is low severity.
- 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:
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.
- 8d ago First seen · 83 lines · 34 tokens per session scan A 17c11ea9e238
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.
Other agents, from other repositories
code-reviewer
Reviews code for correctness, security, and convention adherence. Use PROACTIVELY after writing or modifying code.
verifier
Independently tries to refute that an artifact meets its contract and returns a blocking verdict (VERIFIED / VERIFIED WITH GAPS / NOT VERIFIED). Use to adversarially check work another agent produced - never its own.
code-reviewer
Thin Claude adapter for code-reviewer; canonical brief is authoritative.
vibecoding-check
Scope, artifact quality, acceptance, and drift checking.
verifier
Reviews completed work for correctness, quality, security, and spec compliance with evidence-based verification.
Demonstrate
Agent for demonstrating VS Code features.