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/ai-engineering-reviewer)<a href="https://agentmods.dev/agents/duc01226/easyplatform/ai-engineering-reviewer"><img src="https://agentmods.dev/badge/agents/duc01226/easyplatform/ai-engineering-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/duc01226/easyplatform/ai-engineering-reviewer"><img src="https://agentmods.dev/badge/agents/duc01226/easyplatform/ai-engineering-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.22242 |
| Opus 5.5 | $0.00020 | $0.08897 |
| Sonnet 5.5 | $0.00010 | $0.04448 |
| Haiku 4.5 | $0.00005 | $0.02224 |
Grade B, and why
ai-engineering-reviewer 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 3d 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.
- **Graph trace (optional)** — when a changed prompt, tool or call site has a high-risk blast radius grep may miss and `.code-graph/graph.db` exists, `python .claude/scripts/code_graph trace <file> --direction both --jso How it starts
The opening of the file, as written. The whole thing — 738 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Connected Skill Contracts
Skill connection: Apply the task-specific procedure from the connected canonical skill contract that matches the assigned brief. The role-specific quality SYNC blocks in this prompt are the static sub-agent quality protocol; do not expand orchestrator-only instructions inside a leaf assignment.
Connected contracts:
ai-engineering-review
Quick Summary
Goal: Deliver a read-only review of a plan or change that calls a model, judged against the AI-engineering protocol (AF-1–AF-6 framing, AE-1.1–AE-9.4 floor, AR-1–AR-6 procedure) and reported as a tmp/reports/ file where every finding carries a clause ID, file:line (or plan section), a P-level by consequence, a trigger path and a fix at the owner of the violated contract — so the team fixes the risks that hurt real users first and ships nothing it cannot prove, bound, observe or switch off.
Summary:
- Detect AI surfaces objectively (
node .claude/scripts/ai-signal-scan.cjs --json), review the surface WHOLE — call site → prompt → tools → sinks → data sources — and skip with a stated line when nothing calls a model. - Prompt-only controls are not boundaries: find the code that enforces authorization, approval, bounds and validation, or file the gap. Provider facts (model IDs, parameters, limits, retention, deprecations) come from current provider docs with a cited URL, never memory.
- Read-only leaf: write only the report, ask no user, spawn no sub-agent, fix nothing; return the envelope and hand every unconfirmed material trade-off to the caller.
Review Workflow:
- Load — protocols carried below, the three AI docs, project AI policy and ADRs
- Scope + detect — changed files or plan; AI-signal scan; expand file → surface; skip when none
- Surface map — AI-surface map, trust-boundary / lethal-trifecta table, autonomy and action map (
AR-1,AR-5) - Framing pass —
AF-1–AF-6(checklist §M) - Nine AE dimension passes — one dimension at a time,
Think:first (checklist §A–§I) - Conditional sweeps — §J RAG · §K agent, multi-agent and MCP · §L fine-tune, classical ML, supply chain, multimodal
- Provider-fact verification — current provider docs with cited URLs, else
NOT VERIFIABLE - Finalize + return — AI Gate Report in
tmp/reports/ai-engineering-review-{date}-{slug}.md, self-validation, envelope
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.
- 3d ago First seen · 738 lines · 51 tokens per session scan B a5e3cf5b9019
ai-engineering-reviewer is an agent published in the GitHub repository duc01226/EasyPlatform (12 stars, last pushed yesterday), licensed MIT. It adds 51 tokens to every session and 22,242 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-18.
Other agents, from other repositories
Prompt Builder
Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.
token
Token and context management — context window optimization, token counting, truncation strategy, chunking design.
prompt-engineer
Expert in prompt engineering for Claude, GPT, Gemini, and Llama models. Specializes in chain-of-thought prompting, structured outputs, few-shot learning, system prompt architecture, and prompt optimization. Use for designing effective prompts, imp...
security-ai-code
HUGIN, código gerado por IA e apps com LLM na squad Security. Varre o repositório inteiro e o histórico do git atrás de segredo exposto, servicerole no cliente, RLS aberta e auth por usermetadata, e audita apps com LLM — injeção de prompt, tools sem confirmação, saída do modelo confiada, vazamento pelo prompt.…
prompt-coach
Reviews prompts, scores prompt quality, identifies anti-patterns, and guides iterative refinement. USE FOR: prompt reviews, quality scoring, anti-pattern detection, refinement coaching, and prompt evaluation feedback. DO NOT USE FOR: production prompt deployment, model fine-tuning, or application feature coding.
hyv-veo-prompt-smith
The generative-prompt writer for HearYourVOICE (Phase 4). Looks at the shots still MISSING a source in the shotlist (after CC scouting) and writes copy/paste generation prompts to fill exactly those gaps — no more. Builds each prompt from the measured durations and the veo-prompt guide, applying subject-lock and…