learning-loop

learning-loop is a skill for Claude Code, Codex from robium-ai/robium. It costs 215 tokens per session (2,942 once invoked), scanned A, original, MIT.

A workflow for turning captured notes, flags, and lessons into evidence-based observations and proposed updates to coding-agent skills. Proposed changes go into reviewable pull requests, and a person merges them.

In plain words
What is it for?
Use it to consolidate learnings, draft skill updates, clean up duplicate or outdated guidance, compare competing edits, verify examples, and inspect the learning system’s status.
Why use it?
It gives learning from past sessions a reviewable path instead of leaving lessons scattered or changing skills directly without oversight.

Skill for Claude CodeCodex

Part of the robium plugin — 72 skills, 1 agent, 6 hooks 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 skills/robium-ai/robium/0.2.0
Any agent
npx skills add robium-ai/robium --skill 0.2.0
Clone the repo
git clone --depth 1 https://github.com/robium-ai/robium

Made for: Claude Code, Codex.

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/0.2.0.svg)](https://agentmods.dev/skills/robium-ai/robium/0.2.0)
Your own site
<a href="https://agentmods.dev/skills/robium-ai/robium/0.2.0"><img src="https://agentmods.dev/badge/skills/robium-ai/robium/0.2.0.svg" alt="Measured on agentmods" height="20"></a>
Per session 215 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,942 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 $0.00215 $0.02942
Opus 5 $0.00108 $0.01471
Sonnet 5 $0.00043 $0.00588
Haiku 4.5 $0.00021 $0.00294

Measured 5d ago against content hash d09d2d316b03, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

archive/learning-loop/0.2.0/SKILL.md · 217 lines

How it starts

The opening of the file, as written. The whole thing — 217 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–§10). 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.
  • Contested or structural edits ("experiment", "A/B this edit", "try competing fixes") — description rewrites, restructures, competing fixes where the right answer isn't obvious enough for a single draft.
  • Scheduled example verification ("deep verify", "verify the examples") — promoting pinned examples/references content from status: unverified once its evals.yaml fixture passes.
  • 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, run_variants.py, deep_verify.py, run_task_checks.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.
  • Variants are deltas, never rewrites. Full-file candidate rewrites are forbidden (context collapse); a variant that apply_deltas refuses is a broken candidate, not a contender.

Read the full file on GitHub · 217 lines

Files

What ships with it

5 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. 5d ago First seen · 217 lines · 215 tokens per session scan A d09d2d316b03

Subscribe to this mod's changes

learning-loop is a skill published in the GitHub repository robium-ai/robium (9 stars, last pushed 7d ago), licensed MIT. It adds 215 tokens to every session and 2,942 once invoked, about $0.0011 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.

Related

Other skills, from other repositories

data-charts-tako

Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.

gooseworks-ai/goose-skills · 35 tokens

apollo-lead-finder

Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Creates Apollo lists. Deduplicates against existing contacts by LinkedIn URL.

gooseworks-ai/goose-skills · 51 tokens

monorepo-management

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

wshobson/agents · 54 tokens

browse-and-evaluate

Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.

MoizIbnYousaf/Ai-Agent-Skills · 43 tokens

render-airdrop-carousel

Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…

gooseworks-ai/goose-skills · 207 tokens

render-3d-product-showcase

Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…

gooseworks-ai/goose-skills · 159 tokens