best-practice-extractor

best-practice-extractor is an agent for Claude Code from gpt-cmdr/ras-commander. It costs 46 tokens per session (795 once invoked), scanned A, original, MIT.

An agent that examines past conversations to find recommended practices, successful approaches, and lessons worth documenting. A best practice is a method that has proved useful and may be worth repeating.

In plain words
What is it for?
Use it when looking for best practices, successful patterns, lessons learned, or approaches that should be formalized for future work.
Why use it?
Useful advice can be buried in long conversation histories. This agent helps collect recurring guidance and successful patterns in one place.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions AGENTS.md.

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 agents/gpt-cmdr/ras-commander/best-practice-extractor
Clone the repo
git clone --depth 1 https://github.com/gpt-cmdr/ras-commander

Made for: Claude Code.

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 best-practice-extractor

README.md
[![agentmods](https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/best-practice-extractor.svg)](https://agentmods.dev/agents/gpt-cmdr/ras-commander/best-practice-extractor)
Your own site
<a href="https://agentmods.dev/agents/gpt-cmdr/ras-commander/best-practice-extractor"><img src="https://agentmods.dev/badge/agents/gpt-cmdr/ras-commander/best-practice-extractor.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 795 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00046 $0.00795
Opus 5 $0.00023 $0.00398
Sonnet 5 $0.00009 $0.00159
Haiku 4.5 $0.00005 $0.00080

Measured 6d ago against content hash aa283175c84b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

best-practice-extractor 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 6d 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/agents/best-practice-extractor.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Best Practice Extractor

Extract best practices and successful strategies from conversation history.

Purpose

Analyze conversations to identify:

  • Explicit best practice recommendations
  • Successful approaches worth repeating
  • Patterns worth formalizing
  • Lessons learned

Detection Keywords

BEST_PRACTICE_KEYWORDS = [
    "best practice", "should always", "always use", "never use",
    "recommended", "prefer", "important to", "make sure to",
    "don't forget", "remember to", "key is to", "the pattern is",
    "rule of thumb", "guideline", "standard", "convention"
]

Analysis Method

1. Explicit Practice Detection

for msg in messages:
    for kw in BEST_PRACTICE_KEYWORDS:
        if kw in msg.lower():
            # Extract context around keyword
            practices.append({
                'practice': extract_practice(msg, kw),
                'context': msg[:500],
                'session_id': session_id
            })

2. Success Pattern Detection

SUCCESS_INDICATORS = [
    "works great", "perfect", "exactly what", "this is the way",
    "much better", "finally works", "correct approach"
]

for msg in messages:
    if any(ind in msg.lower() for ind in SUCCESS_INDICATORS):
        # Extract what was successful
        successes.append(analyze_success_context(msg))

3. Categorization

CATEGORIES = {
    "code": ["function", "class", "method", "code", "implementation"],
    "workflow": ["workflow", "process", "approach", "steps"],
    "documentation": ["document", "readme", "comment", "docstring"],
    "testing": ["test", "validate", "verify", "check"],
    "architecture": ["pattern", "design", "structure", "organization"]
}

Output Format

{
  "best_practices": [
    {
      "category": "code",
      "practice": "Use @staticmethod for state-free operations in ras-commander",
      "rationale": "Cleaner API, no instantiation needed, consistent with library pattern",
      "implementation": "Add @staticmethod decorator, call directly on class",
      "session_ids": ["abc123"],
      "evidence": ["The static class pattern provides..."]
    }
  ]
}

Read the full file on GitHub · 125 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. 6d ago First seen · 125 lines · 46 tokens per session scan A aa283175c84b

Subscribe to this mod's changes

best-practice-extractor is an agent published in the GitHub repository gpt-cmdr/ras-commander (79 stars, last pushed yesterday), licensed MIT. It adds 46 tokens to every session and 795 once invoked, about $0.0002 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 2026-08-30.