learning

learning is a skill for Claude Code, Codex from adonai-labs/agent-runway. It costs 58 tokens per session (782 once invoked), scanned A, original, MIT.

A tool for saving a reusable lesson from completed development work in the project's memory files. The lesson can record a decision, recurring practice, failure, or safety rule.

In plain words
What is it for?
Use it to remember architecture decisions, testing requirements, operational safeguards, reasoning patterns, or repeated implementation conventions.
Why use it?
It prevents useful project knowledge from being lost after the current task and helps future work follow established conventions.

Skill for Claude CodeCodex

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

Good fit Use it to remember architecture decisions, testing requirements, operational safeguards, reasoning patterns, or repeated implementation conventions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adonai-labs/agent-runway/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 adonai-labs/agent-runway --skill learning
Clone the repo
git clone --depth 1 https://github.com/adonai-labs/agent-runway

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 learning

README.md
[![agentmods](https://agentmods.dev/badge/skills/adonai-labs/agent-runway/learning.svg)](https://agentmods.dev/skills/adonai-labs/agent-runway/learning)
Your own site
<a href="https://agentmods.dev/skills/adonai-labs/agent-runway/learning"><img src="https://agentmods.dev/badge/skills/adonai-labs/agent-runway/learning.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 782 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.
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 $0.00058 $0.00782
Opus 5 $0.00029 $0.00391
Sonnet 5 $0.00012 $0.00156
Haiku 4.5 $0.00006 $0.00078

Measured 7d ago against content hash 32a735256218, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

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 7d 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.

src/core/skills/learning/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learning

Invoke Skill

@learning <lesson or observation>

Examples:

  • @learning we do not use generic repositories in this service
  • @learning tests must use Testcontainers because SQLite hides provider issues
  • @learning auth changes need a manual permission matrix check

What this skill does

Turns a useful lesson into a concise memory entry under .agent-runway/memory/.

Use it for reusable project knowledge, not for run history. If the information only explains what happened in the current session, use @checkpoint instead.


Workflow

1. Classify the lesson

Choose exactly one target file:

Target Use when
.agent-runway/memory/project-decisions.md Architecture, product, API, schema, dependency, or team decision
.agent-runway/memory/execution-memory.md Operational guardrail, validation step, setup issue, release/deploy lesson
.agent-runway/memory/reasoning-memory.md A recommendation changed after trade-off analysis or contrarian evidence
.agent-runway/memory/recurring-patterns.md Repeated implementation convention, naming, module, or workflow pattern
.agent-runway/memory/common-failures.md Repeated bug class, test miss, migration issue, integration failure, or review finding
.agent-runway/memory/testing-notes.md Test strategy, fixture, environment, or coverage lesson
.agent-runway/memory/review-findings.md Review pattern likely to appear again
.agent-runway/memory/ticket-quality-notes.md Ticket/spec quality issue or acceptance criteria lesson

If more than one file could fit, pick the narrowest reusable target.

2. Validate it is worth saving

Save only if the lesson is:

  • durable: likely to matter again
  • specific: tied to this project or stack
  • actionable: changes future behavior
  • non-sensitive: no secrets, credentials, customer data, or private incident detail

If it is too vague, ask one clarifying question. If it is only session state, recommend @checkpoint.

Read the full file on GitHub · 98 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. 7d ago First seen · 98 lines · 58 tokens per session scan A 32a735256218

Subscribe to this mod's changes

learning is a skill published in the GitHub repository adonai-labs/agent-runway (2 stars, last pushed 17d ago), licensed MIT. It adds 58 tokens to every session and 782 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 2026-08-31.

Related

Other skills, from other repositories

mindos

MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…

GeminiLight/MindOS · 136 tokens

init-workspace-documentation

Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.

griddynamics/rosetta · 10 tokens

tour

Interactive onboarding walkthrough for a new engineer. Use for "give me a tour", "onboard me", "walk me through the codebase".

drafthq/draft · 31 tokens

spec-harness-build

Run the SDD pipeline over tasks.md: implement → test → VERIFY → review, one task at a time, under the ratchet. Use when Malik says 'build it', 'run the pipeline', 'implement the tasks', or 'ship this feature'. Each task gated by the separate verifier; lessons harvested by learn.

chohra-med/expo_boilerplate · 0 tokens

fec-image-generation

A workflow for creating or editing images and diagrams, from posters and product mockups to academic graphics, illustrations, and system maps. For text-heavy technical diagrams, it can use editable sources such as Mermaid, SVG, HTML, or canvas before exporting an image.

bovinphang/frontend-craft · 256 tokens

totem-compiled-rules

Compiled architectural rules and lessons from the Totem knowledge base. Load this when reviewing code for pattern violations or architectural drift.

mmnto-ai/totem · 31 tokens