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/improve-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/improve-agent)<a href="https://agentmods.dev/commands/sarkarsaurabh27/agent-loop-learning/improve-agent"><img src="https://agentmods.dev/badge/commands/sarkarsaurabh27/agent-loop-learning/improve-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 | $0.00997 |
| Opus 5 | $0.00000 | $0.00498 |
| Sonnet 5 | $0.00000 | $0.00199 |
| Haiku 4.5 | $0.00000 | $0.00100 |
Grade A, and why
improve-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 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.
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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/improve-agent
Goal: execute on issues found. Apply concrete, benchmark-backed improvements to the agent in this repo.
There are two entry paths:
- Findings already exist (the user just ran
/review-agent, pasted a review, or named specific issues) → skip straight to executing on those. - No findings yet → first run the
/review-agentflow internally to surface gaps, then execute on the top issues.
Works for any LLM agent framework — LangChain, LangGraph, AutoGen, CrewAI, OpenAI Agents SDK, Semantic Kernel, custom loops, etc. Recommendations are framework-agnostic unless the user asks for framework-specific code.
Usage
/improve-agent → full system pass (review first if needed, then execute)
/improve-agent orchestration → focus on multi-agent design
/improve-agent prompting → focus on prompt structure
/improve-agent memory → focus on context & memory
/improve-agent tools → focus on tool design
/improve-agent verification → focus on testing & verification
/improve-agent security → focus on security & permissions
/improve-agent performance → focus on startup & latency
/improve-agent <paste findings> → execute on the pasted findings directly
Instructions
-
Check whether findings already exist in the conversation.
- If the user pasted a review, named specific issues, or just ran
/review-agent— use those findings as the work list and skip to step 4. - Otherwise, continue to step 2 to generate them.
- If the user pasted a review, named specific issues, or just ran
-
Explore the current repo first — do not ask the user for anything yet. Search for agent-related code:
- Files matching
*agent*,*tool*,*prompt*,*chain*,*workflow*insrc/,lib/,app/, root - Imports of agent frameworks:
langchain,langgraph,openai,anthropic,autogen,crewai - System prompt definitions, tool definitions, agent loop logic
CLAUDE.md,AGENTS.md, or any README describing the agent architecture
- Files matching
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 · 71 lines · 0 tokens per session scan A 613e913747eb
improve-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 997 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.