autonomous-lesson-learning

autonomous-lesson-learning is a skill for Claude Code, Codex from Fmarzochi/EGC. It costs 54 tokens per session (1,435 once invoked), scanned A, original, Apache-2.0.

An autonomous work loop that recalls lessons before each iteration and saves or reinforces lessons after successes and failures. It uses stored lessons so later iterations can avoid repeating known mistakes.

In plain words
What is it for?
It is for tasks such as fixing many lint errors, increasing test coverage, or processing an issue list through repeated agent cycles.
Why use it?
It makes long-running, repeated work less likely to lose useful experience between iterations or sessions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for tasks such as fixing many lint errors, increasing test coverage, or processing an issue list through repeated agent cycles.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fmarzochi/egc/autonomous-lesson-learning
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.

Any agent
npx skills add Fmarzochi/EGC --skill autonomous-lesson-learning
Clone the repo
git clone --depth 1 https://github.com/Fmarzochi/EGC

Made for: Claude Code, Codex.

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 autonomous-lesson-learning

README.md
[![agentmods](https://agentmods.dev/badge/skills/fmarzochi/egc/autonomous-lesson-learning.svg)](https://agentmods.dev/skills/fmarzochi/egc/autonomous-lesson-learning)
Your own site
<a href="https://agentmods.dev/skills/fmarzochi/egc/autonomous-lesson-learning"><img src="https://agentmods.dev/badge/skills/fmarzochi/egc/autonomous-lesson-learning.svg" alt="Measured on agentmods" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,435 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00054 $0.01435
Opus 5 $0.00027 $0.00718
Sonnet 5 $0.00011 $0.00287
Haiku 4.5 $0.00005 $0.00144

Measured 5d ago against content hash d83a81b03940, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

autonomous-lesson-learning 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 5d 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.

skills/ai/autonomous-lesson-learning/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autonomous Lesson Learning

Run an autonomous work loop that gets smarter every iteration. This skill is pure orchestration: it combines the loop patterns from continuous-agent-loop / autonomous-loops with the lesson_recall, lesson_save, and lesson_reinforce tools from the egc-memory MCP server. It does not reimplement loops and it does not add a new lesson store.

Works in any harness that has the egc-memory MCP server registered (all EGC Tier 1/2/3 targets). Nothing here is platform-specific: the loop is plain instruction-following and the memory calls are standard MCP tool calls.

When to Activate

  • Running a long multi-iteration task autonomously (fix all lint errors, raise coverage, burn down an issue list) where repeating a known mistake is expensive
  • Resuming a class of work that has failed before and the failure modes are worth remembering across sessions
  • Any continuous-agent-loop pattern (Sequential Pipeline, Continuous PR Loop) where you also want cross-session learning

Use a plain loop (/loop-start, continuous-agent-loop) instead when the task is one-off, trivial, or exploratory throwaway work where lessons would be noise.

The Cycle

+--------------------------------------------------------+
|  AUTONOMOUS LESSON LEARNING ITERATION                  |
|                                                        |
|  1. RECALL   lesson_recall({ query }) for the current  |
|              step BEFORE acting                        |
|  2. APPLY    adjust the plan using recalled lessons;   |
|              lesson_reinforce({ id }) each lesson that |
|              proved relevant                           |
|  3. ACT      execute one loop iteration (implement,    |
|              test, fix) per continuous-agent-loop      |
|  4. RECORD                                             |
|     - failure -> known lesson matches?                 |
|         yes -> lesson_reinforce({ id })                |
|         no  -> lesson_save({ content, context })       |
|     - new pattern that worked well?                    |
|         -> lesson_save with prescriptive wording       |
|  5. CHECK    stop condition met? done : goto 1         |
+--------------------------------------------------------+

Read the full file on GitHub · 118 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. 5d ago First seen · 118 lines · 54 tokens per session scan A d83a81b03940

Subscribe to this mod's changes

autonomous-lesson-learning is a skill published in the GitHub repository Fmarzochi/EGC (49 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 1,435 once invoked, about $0.0003 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 2026-09-03.