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.
npx agentmods add commands/sarkarsaurabh27/agent-loop-learning/review-agentgit clone --depth 1 https://github.com/sarkarsaurabh27/agent-loop-learningWrote 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/commands/sarkarsaurabh27/agent-loop-learning/review-agent)<a href="https://agentmods.dev/commands/sarkarsaurabh27/agent-loop-learning/review-agent"><img src="https://agentmods.dev/badge/commands/sarkarsaurabh27/agent-loop-learning/review-agent.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 | $0.00000 | $0.00737 |
| Opus 5 | $0.00000 | $0.00368 |
| Sonnet 5 | $0.00000 | $0.00147 |
| Haiku 4.5 | $0.00000 | $0.00074 |
Grade A, and why
review-agent 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review-agent
Goal: review and show only. Audit an agent design against the best-practice reference docs and surface findings. Do not modify any files, write code, or execute fixes. The user (or /improve-agent) decides what to do with the findings.
Works for any LLM agent framework — LangChain, LangGraph, AutoGen, CrewAI, OpenAI Agents SDK, custom loops, etc. The practices are framework-agnostic.
Instructions
-
Explore the current repo first — do not ask the user for anything yet. Look for agent-related code by searching for common patterns:
- Files matching
*agent*,*tool*,*prompt*,*chain*,*workflow*insrc/,lib/,app/, root - Imports of agent frameworks:
langchain,langgraph,openai,anthropic,autogen,crewai,pydantic - System prompt definitions, tool definitions, agent loop logic
CLAUDE.md,AGENTS.md,GEMINI.md, or any README describing the agent architecture
Read the most relevant files to understand the agent design. Only ask the user if you genuinely cannot find any agent-related code after exploring.
- Files matching
-
Read all 9 best-practice docs from
best-practices/in this repo. -
Produce a structured gap analysis using the format below. This is the output — do not edit any project files, do not write fixes, do not run shell commands beyond what's needed to explore the repo.
Agent Review: [agent name or "Unnamed Agent"]
Summary (2–3 sentences on the overall design)
Dimension-by-dimension audit
For each of the 9 dimensions below, score the design:
- ✅ Solid — clearly covered
- ⚠️ Partial — present but missing something important
- ❌ Gap — not addressed or actively violating the practice
| # | Dimension | Score | Finding |
|---|---|---|---|
| 01 | Multi-agent orchestration | ||
| 02 | Worker prompting | ||
| 03 | Context & memory | ||
| 04 | Tool design | ||
| 05 | Verification & testing | ||
| 06 | Security & permissions | ||
| 07 | Prompt engineering | ||
| 08 | Performance & startup |
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 · 69 lines · 0 tokens per session scan A 638f916d488b
review-agent is a command published in the GitHub repository sarkarsaurabh27/agent-loop-learning (3 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 737 tokens. 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.