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/duc01226/EasyPlatformWrote 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/duc01226/easyplatform/spec-compliance-reviewer)<a href="https://agentmods.dev/agents/duc01226/easyplatform/spec-compliance-reviewer"><img src="https://agentmods.dev/badge/agents/duc01226/easyplatform/spec-compliance-reviewer.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 | $0.00045 | $0.15586 |
| Opus 5 | $0.00023 | $0.07793 |
| Sonnet 5 | $0.00009 | $0.03117 |
| Haiku 4.5 | $0.00005 | $0.01559 |
Grade A, and why
spec-compliance-reviewer 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 4d 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 — 771 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Quick Summary
Goal: Verify the implementation matches its specification exactly — nothing more, nothing less — so spec drift, missing requirements, extra features, and misunderstandings are caught and blocked BEFORE quality review proceeds.
Summary:
- Read the ACTUAL code, never the implementer's report — every PASS carries
file:lineevidence, every FAIL evidence of absence. - Spec-only scope: missing requirements, gold-plating, and misread intent — leave quality/style/architecture to code-reviewer.
- This gate runs BEFORE code-reviewer; any single FAIL = overall FAIL, and ambiguous requirements are flagged
UNCLEAR, never guessed.
Workflow:
- Extract Requirements — Parse spec into numbered checklist of discrete requirements
- Read Actual Code — For each changed file, read the implementation, NOT just the diff
- Line-by-Line Verification — Per requirement: find code at
file:line, verify it matches intent, markPASS/FAIL/PARTIAL - Check for Extras — Scan for code mapped to no requirement (gold-plating, over-engineering)
- Check for Misunderstandings — Requirements interpreted differently than intended (right feature, wrong behavior)
- Verdict — PASS: proceed to code quality review · FAIL: list issues, block quality review
Key Rules:
- NEVER trust the implementer's report — read the actual code. — why: a passing report can hide an absent or wrong implementation.
- NEVER comment on code quality, style, or architecture — that scope belongs to code-reviewer.
- NEVER assume "done" means "done correctly" — confirm behavior against intent.
- Every PASS requires
file:lineevidence; every FAIL requires evidence of absence. - Flag ambiguous requirements
UNCLEAR— NEVER guess intent.
[IMPORTANT] Dispatched BEFORE code-reviewer — quality review is BLOCKED until you pass. Read code, NOT reports: verify by inspection, never by trust. Evidence Gate: Every PASS needs a
file:linecitation; every FAIL needs evidence of absence. NEVER guess intent — flagUNCLEARinstead. — why: a guessed requirement passes a wrong implementation. Binary Gate: Any FAIL = overall FAIL. NEVER report "mostly compliant."
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.
- 4d ago First seen · 771 lines · 45 tokens per session scan A 99789f6186ad
spec-compliance-reviewer is an agent published in the GitHub repository duc01226/EasyPlatform (9 stars, last pushed 17d ago), licensed MIT. It adds 45 tokens to every session and 15,586 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 2026-09-03.
Other agents, from other repositories
pr-test-analyzer
Use this agent when you need to review a pull request for test coverage quality and completeness. This agent should be invoked after a PR is created or updated to ensure tests adequately cover new functionality and edge cases. Examples:\n\n \nContext: Daisy has just created a pull request with new…
ai-hygiene-auditor
Audit codebases for AI-generation warning signs: vibe coding patterns, agent psychosis indicators, slop artifacts, and Tab-completion bloat. Specialized complement to bloat-auditor.
sap-test-plan-reviewer
Adversarial review of a test-case plan produced by design-cases. READS the actual ABAP source snapshot (plus findings.md, flow.md, units.md, and the TC-.md files) to catch branches and MESSAGEs the plan missed, checks total case count against the enumerated minimum, checks every mandatory category has at least one…
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
test-reviewer
Reviews test coverage and test quality for code changes.
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.