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.
npx skills add Fmarzochi/EGC --skill autonomous-lesson-learninggit clone --depth 1 https://github.com/Fmarzochi/EGCWrote 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.
[](https://agentmods.dev/skills/fmarzochi/egc/autonomous-lesson-learning)<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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-looppattern (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 |
+--------------------------------------------------------+
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.
- 5d ago First seen · 118 lines · 54 tokens per session scan A d83a81b03940
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.
Other skills, from other repositories
mem9
Persistent cloud memory plugin for OpenClaw. This document routes setup, troubleshooting, and uninstall flows and defines config boundaries.
init
Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.
ijfw-handoff
Session handoff generation and loading. Trigger: session end, context full, /handoff.
lov-search-chat
A local search tool for recalling relevant parts of earlier AI conversations from an indexed memory store. It returns matching sessions and identifiable excerpts from the original conversations.
chatcrystal-debug-recall
Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.
learn-this
Teach the user a topic and persist what they learn as queryable vault memory, grounded in NotebookLM. Vault-native companion to /teach.