agent-loop-learning CLAUDE.md

agent-loop-learning CLAUDE.md is an instructions file for coding agents from sarkarsaurabh27/agent-loop-learning. It costs 507 tokens per session, scanned A, original, MIT.

A project guide and reference library for reviewing and improving AI agents. It contains learning documents about how agents coordinate work, use prompts, retain context, call tools, verify results, handle security, and manage performance.

In plain words
What is it for?
Use it to audit an agent, learn about a specific design topic, or work through improvements. Its included commands load best-practice documents, review an agent, and suggest targeted changes.
Why use it?
It gives developers a common place to learn agent design practices and inspect an agent against them. The documents include benchmark figures and sources for comparing design choices.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/sarkarsaurabh27/agent-loop-learning/claude-md
Clone the repo
git clone --depth 1 https://github.com/sarkarsaurabh27/agent-loop-learning

Wrote 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.

agentmods badge for agent-loop-learning CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sarkarsaurabh27/agent-loop-learning/claude-md.svg)](https://agentmods.dev/instructions/sarkarsaurabh27/agent-loop-learning/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sarkarsaurabh27/agent-loop-learning/claude-md"><img src="https://agentmods.dev/badge/instructions/sarkarsaurabh27/agent-loop-learning/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 507 This file is loaded in full into every session.
When invoked 507 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00507 $0.00507
Opus 5 $0.00253 $0.00253
Sonnet 5 $0.00101 $0.00101
Haiku 4.5 $0.00051 $0.00051

Measured 4d ago against content hash 0057b2dde05d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-loop-learning CLAUDE.md 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.

CLAUDE.md · 32 lines

How it starts

The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Loop Learning — Project Context

This repo is a reference library and skill toolkit for auditing, reviewing, and improving LLM-based agent systems.

What's here

  • best-practices/ — 9 curated documents covering orchestration, prompting, memory, tools, verification, security, performance, and benchmarks. Each doc includes benchmark numbers with primary sources.
  • .claude/commands/ — Slash-command skills for local Claude Code agents:
    • /review-agent — Audit any agent design against all best-practice docs
    • /improve-agent — Targeted improvement recommendations for a specific agent component
    • /best-practices — Load a specific best-practice doc by topic keyword

How to use this repo

  1. As an audit: open a design doc, run /review-agent to get a structured gap analysis
  2. As a learning loop: run /improve-agent <component> to get concrete, benchmark-backed improvement suggestions
  3. As a reference: run /best-practices <topic> to pull the relevant doc into context

Best practices index

# File Topic
01 best-practices/01-multi-agent-orchestration.md Coordinator/worker split, four-phase model, concurrency
02 best-practices/02-worker-prompting.md Worker prompt structure, scaffold design, stop conditions
03 best-practices/03-context-and-memory.md 6-layer context pipeline, 3-layer memory, RAG patterns
04 best-practices/04-tool-design.md Tool classification, security properties, streaming
05 best-practices/05-verification-and-testing.md Verification patterns, VCR fixtures, forced acknowledgment
06 best-practices/06-security-and-permissions.md Denial circuit breakers, injection defense, token hygiene
07 best-practices/07-prompt-engineering.md Cache boundaries, prompt anchors, system prompt structure
08 best-practices/08-performance-and-startup.md Circuit breakers, diminishing-returns detector, wake lock
09 best-practices/09-benchmarks-reference.md All benchmark numbers with caveats and sources

Read the full file on GitHub · 32 lines

Changes

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.

  1. 4d ago First seen · 32 lines · 507 tokens per session scan A 0057b2dde05d

Subscribe to this mod's changes

agent-loop-learning CLAUDE.md is an instructions file published in the GitHub repository sarkarsaurabh27/agent-loop-learning (3 stars, last pushed 3mo ago), licensed MIT. It adds 507 tokens to every session, about $0.0025 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.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,345 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

next.js AGENTS.md

Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens