agent-loop-learning copilot-instructions.md

A set of instructions for reviewing and improving AI-agent systems. It connects common questions about prompts, memory, tools, testing, security, and performance to relevant best-practice documents.

In plain words
What is it for?
Use it when designing agent architecture, writing prompts, managing context or retrieval, creating tools, checking security, or planning tests and verification.
Why use it?
It reduces the need to search through a reference library before answering technical questions about agents. It also gives reviews a consistent workflow.

Instructions file for GitHub Copilot

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/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/sarkarsaurabh27/agent-loop-learning

Made for: GitHub Copilot.

Per session 675 This file is loaded in full into every session.
When invoked 675 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 $0.00675 $0.00675
Opus 5 $0.00338 $0.00338
Sonnet 5 $0.00135 $0.00135
Haiku 4.5 $0.00068 $0.00068

Measured 2d ago against content hash fdd0aa4f353b, 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 copilot-instructions.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 2d 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.

.github/copilot-instructions.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Copilot Instructions — Agent Loop Learning

This repo is a reference library for auditing, reviewing, and improving LLM-based agent systems. The best-practice docs in best-practices/ are framework-agnostic and apply to any agent on any model.

When to use the best-practice docs

Always read the relevant doc before answering questions about:

  • Agent architecture or design patterns
  • Prompt structure, system prompts, or worker prompts
  • Memory, context windows, or RAG pipelines
  • Tool design or function calling
  • Testing or verification strategies
  • Security, permissions, or prompt injection
  • Performance, latency, or startup behavior

Doc → topic mapping

If user asks about... Read this file
Multi-agent systems, orchestration, coordinator/worker best-practices/01-multi-agent-orchestration.md
Worker prompts, scaffolding, stop conditions best-practices/02-worker-prompting.md
Memory, context management, RAG best-practices/03-context-and-memory.md
Tool design, function calling best-practices/04-tool-design.md
Testing, verification, self-reflection best-practices/05-verification-and-testing.md
Security, injection, permissions best-practices/06-security-and-permissions.md
Prompt engineering, cache, system prompts best-practices/07-prompt-engineering.md
Performance, startup, circuit breakers best-practices/08-performance-and-startup.md
Benchmark numbers, citations best-practices/09-benchmarks-reference.md

Review workflow

When asked to review or audit an agent design:

  1. Explore the current repo first — do not ask the user for anything. Search for agent-related files (*agent*, *tool*, *prompt*, *chain*, *workflow*), framework imports (langchain, openai, anthropic, autogen, crewai), system prompt definitions, and any CLAUDE.md, AGENTS.md, or README describing the architecture. Read the relevant files. Only ask if no agent code is found.
  2. Read all 9 docs.
  3. Score each dimension: ✅ Solid / ⚠️ Partial / ❌ Gap.
  4. Return scorecard, top 3 prioritized improvements (with benchmark citations), and callouts for what's strong.

Read the full file on GitHub · 50 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. 2d ago First seen · 50 lines · 675 tokens per session scan A fdd0aa4f353b

Subscribe to this mod's changes

agent-loop-learning copilot-instructions.md is an instructions file published in the GitHub repository sarkarsaurabh27/agent-loop-learning (3 stars, last pushed 3mo ago), licensed MIT. It adds 675 tokens to every session, about $0.0034 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