learning-loop

learning-loop is a skill for Claude Code from robium-ai/robium. It costs 175 tokens per session (1,972 once invoked), scanned A, original, MIT.

A session workflow for turning captured notes and observed problems into evidence-based improvements to coding-agent skills.

In plain words
What is it for?
Use it to consolidate learnings, prepare skill-edit pull requests, refine the skill catalogue, or check the health of the learning process.
Why use it?
It organizes scattered feedback, removes duplicates or stale items, and keeps proposed skill changes reviewable instead of applying them silently.

Skill for Claude Code

Written for Claude Code: UserPromptSubmit hook event. Also seen: reads .claude/ paths.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is uv run scripts/engine/skill_metrics.py # catalog health.

Part of the robium plugin — 72 skills, 1 agent, 6 hooks shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add robium-ai/robium
Claude Code
/plugin install robium

Made for: Claude Code.

Or install robium, the plugin that ships this one along with the rest of its 72 skills, 1 agent, 6 hooks.

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-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/robium-ai/robium/0.1.0.svg)](https://agentmods.dev/skills/robium-ai/robium/0.1.0)
Your own site
<a href="https://agentmods.dev/skills/robium-ai/robium/0.1.0"><img src="https://agentmods.dev/badge/skills/robium-ai/robium/0.1.0.svg" alt="Measured on agentmods" height="20"></a>
Per session 175 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,972 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 $0.00175 $0.01972
Opus 5 $0.00088 $0.00986
Sonnet 5 $0.00035 $0.00394
Haiku 4.5 $0.00017 $0.00197

Measured 6d ago against content hash 63ab91c239bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

learning-loop 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

archive/learning-loop/0.1.0/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learning loop — consolidate, absorb, refine

The engine's session-side pipeline (spec: docs/superpowers/specs/2026-08-01-learning-engine-design.md §5–§8). Capture happens automatically (plugin hooks); this skill turns what was captured into observations, and observations into reviewable skill-edit PRs. The human gate is git merge.

When to use this skill

  • Promoting queue flags and completing dated learnings entries ("consolidate", a Stop-hook nudge, end of a work block).
  • Drafting skill edits from ready observations ("absorb", "update my skills", "run the loop") — output is always a PR branch, never a direct edit.
  • Catalog hygiene passes ("refine the skills") — prune/dedup/staleness through the same delta pipeline, report-first.
  • Loop health ("learning loop status"): queue depth, unabsorbed backlog, eval-suite size, ledger totals.
  • For distilling external repos, use the mining skill; for authoring a new skill from scratch, skill-author.

Key directives

  • Delegation posture: embed — the workflows live here; the deterministic tools live at scripts/engine/ (apply_deltas.py, run_trigger_evals.py, ledger.py, mine_transcripts.py, skill_metrics.py, observations.py, placement.py) and in the plugin hooks (recall).
  • Scripts hold the pen. LLM roles draft deltas and diagnose; apply_deltas.py applies them (snapshot, bump, changelog, sidecars). Never hand-edit a skill during absorb; never bypass the script's refusals — a refusal is a design signal, not an obstacle.
  • Consolidation never touches skills/ content. Its write surface is learnings/, learnings/observations/, and the evidence/evals sidecars — that boundary is what makes it autonomous-safe.
  • Absorb consumes status: ready only. The ready bar (proof ≥ 2 | user-correction | three-part evidence | external official) is enforced by the observations lint; do not absorb around it.
  • Merge is the gate. Every absorb/refine run ends in a PR with the evidence table; no agent merges to main skills/**. Mid-build sessions capture; they never edit skills directly.
  • Dedup against everything seen — including absorbed and rejected observations — or judged-rejected findings reappear forever.
  • One self-check round on consolidator and absorber output: re-read the draft against the source transcript window for misattribution, missed dead-ends, wrong anchors, before writing.

Read the full file on GitHub · 156 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 156 lines · 175 tokens per session scan A 63ab91c239bf

Subscribe to this mod's changes

learning-loop is a skill published in the GitHub repository robium-ai/robium (9 stars, last pushed 8d ago), licensed MIT. It adds 175 tokens to every session and 1,972 once invoked, about $0.0009 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.