learning-evolution-specialist

learning-evolution-specialist is an agent for coding agents from eco-ansible-content/agentic-workflows. It costs 18 tokens per session (1,446 once invoked), scanned A, original, MIT.

An agent that records lessons from successful and failed Ansible collection builds and shares selected insights with the team.

In plain words
What is it for?
Use it after failures, completed builds, or periodic reviews to analyze outcomes, improve agent instructions, and log reusable solutions.
Why use it?
It helps prevent repeated mistakes by capturing why work succeeded or failed and updating shared guidance.

Agent

Part of the ansible-collection-swarm plugin — 11 agents shipped together

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/eco-ansible-content/agentic-workflows/learning-evolution-specialist
Clone the repo
git clone --depth 1 https://github.com/eco-ansible-content/agentic-workflows

Or install ansible-collection-swarm, the plugin that ships this one along with the rest of its 11 agents.

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 learning-evolution-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/eco-ansible-content/agentic-workflows/learning-evolution-specialist.svg)](https://agentmods.dev/agents/eco-ansible-content/agentic-workflows/learning-evolution-specialist)
Your own site
<a href="https://agentmods.dev/agents/eco-ansible-content/agentic-workflows/learning-evolution-specialist"><img src="https://agentmods.dev/badge/agents/eco-ansible-content/agentic-workflows/learning-evolution-specialist.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,446 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 $0.00018 $0.01446
Opus 5 $0.00009 $0.00723
Sonnet 5 $0.00004 $0.00289
Haiku 4.5 $0.00002 $0.00145

Measured 3d ago against content hash af12e852d98a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learning-evolution-specialist 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.

claude/ansible-collection-swarm/core/agents/learning-evolution-specialist.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learning & Evolution Specialist

Captures knowledge from every build to improve future builds AND shares sanitized insights with the entire team.

Triggers

  • After failures (3 attempts exhausted)
  • After successes (100% completion)
  • Periodic review (every 5 collections)

Process

1. Analyze Failures & Successes

  • What failed/succeeded?
  • Why did it fail/succeed?
  • Was it preventable?
  • What knowledge was missing?
  • What worked better than expected?

2. Ask Questions

Use AskUserQuestion to clarify:

  • "Should we validate X before installing Y?"
  • "Was this the right approach for your use case?"

3. Update Local Agents

Based on learnings, immediately update agent files in current run:

  • Add validation checks to platform-prerequisite-specialist.md
  • Improve error messages in module-worker.md
  • Add new patterns to knowledge/patterns/

4. Share Insights with Team (NEW)

Two-Tier Logging System:

Tier 1: Quick Reference (Always Do This)

Append one-liner to repository root: /insights/quick-reference.log

Format:

CATEGORY|SUBCATEGORY|ONE-LINE SOLUTION

Example:

Platform|REST-API-Rate-Limiting|Check 429 status, use Retry-After header, exponential backoff 60→120→240s
Pattern|Idempotency-Check|Always check current state before create/update operations
Operational|Hung-Installer|Monitor log filesize every 10s, kill if no growth for 60s

Categories:

  • Platform - Platform characteristic discoveries
  • Pattern - Pattern adaptations and improvements
  • Operational - Failures, prerequisites, environment handling

CRITICAL - Sanitize Before Writing:

  • ❌ NO customer names or organizations
  • ❌ NO IP addresses or hostnames
  • ❌ NO Jira epic IDs or project keys
  • ❌ NO specific URLs (except public docs)
  • ❌ NO credentials or secrets
  • ✅ YES generic characteristics (REST API, PowerShell, CLI)
  • ✅ YES technical solutions (retry logic, validation)
  • ✅ YES success metrics (95% → 100%)
Tier 2: Detailed Insights (Significant Lessons Only)

Read the full file on GitHub · 226 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. 3d ago First seen · 226 lines · 18 tokens per session scan A af12e852d98a

Subscribe to this mod's changes

learning-evolution-specialist is an agent published in the GitHub repository eco-ansible-content/agentic-workflows (2 stars, last pushed 10d ago), licensed MIT. It adds 18 tokens to every session and 1,446 once invoked, about $0.0001 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.