squads-learn

A procedure for recording useful lessons after software work, such as a completed feature, bug fix, research task, or discovered pattern. It stores the lesson with a short command and optional category, team, and tags.

In plain words
What is it for?
Use it after fixing bugs, completing features, researching a topic, or finding a reusable engineering pattern worth remembering.
Why use it?
It prevents important discoveries from being forgotten between tasks. It can build a shared record of what worked, what failed, and what to repeat.

Skill for Claude CodeCodex

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/agents-squads/squads-cli/squads-learn
Any agent
npx skills add agents-squads/squads-cli --skill squads-learn
Clone the repo
git clone --depth 1 https://github.com/agents-squads/squads-cli

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 609 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 $0.00041 $0.00609
Opus 5 $0.00020 $0.00304
Sonnet 5 $0.00008 $0.00122
Haiku 4.5 $0.00004 $0.00061

Measured 2d ago against content hash e79d0bb66efc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

squads-learn 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 2d 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.

templates/skills/squads-learn/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Capture Learnings

After completing work, capture what you learned so future sessions can benefit.

When to Use

  • After fixing a bug - What was the root cause? How did you find it?
  • After completing a feature - What approach worked? What didn't?
  • After research - What did you discover? What's the key insight?
  • When you notice a pattern - Something that works consistently

How to Capture

Quick Learning (one-liner)

squads learn "The auth token needs to be refreshed after 1 hour, not when the API returns 401"

With Context

squads learn "Always check memory before researching to avoid duplicate work" \
  --squad engineering \
  --category pattern \
  --tags "memory,research,efficiency"

Categories

  • success - Something that worked well
  • failure - Something that didn't work (learn from mistakes)
  • pattern - A reusable approach
  • tip - General advice

Workflow Integration

End of Task

Before marking a task complete, ask yourself:

  1. What worked that I should remember?
  2. What didn't work that I should avoid?
  3. Is there a pattern here worth capturing?

If yes to any → squads learn "<insight>"

Before Similar Tasks

Check existing learnings:

squads learnings search "auth"
squads learnings show engineering --tag auth

Examples

# After fixing a bug
squads learn "PostgreSQL connection pool exhaustion was caused by unclosed transactions in error paths" --category failure --tags db,postgres,connection

# After successful implementation
squads learn "Using TypeScript strict mode caught 3 type errors before runtime" --category success --tags typescript,types

# Noticing a pattern
squads learn "When context exceeds 70%, always run squads memory sync before continuing" --category pattern --tags context,memory

# General tip
squads learn "The gh CLI is faster than the GitHub API for simple operations" --category tip --tags github,cli

View Learnings

squads learnings show <squad>           # Squad's learnings
squads learnings search "<query>"       # Search all learnings
squads learnings show engineering -n 5  # Last 5 for engineering

Read the full file on GitHub · 87 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. 2d ago First seen · 87 lines · 41 tokens per session scan A e79d0bb66efc

Subscribe to this mod's changes

squads-learn is a skill published in the GitHub repository agents-squads/squads-cli (51 stars, last pushed 19d ago), licensed MIT. It adds 41 tokens to every session and 609 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

agent-framework-py-release

Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…

microsoft/agent-framework · 103 tokens

python-package-management

Guide for managing packages in the Agent Framework Python monorepo, including creating new connector packages, versioning, and the lazy-loading pattern. Use this when adding, modifying, or releasing packages.

microsoft/agent-framework · 43 tokens

foundry-hosted-agent-validation

Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.

microsoft/agent-framework · 82 tokens

verify-samples-tool

How to use the verify-samples tool to run, verify, and manage sample definitions in the Agent Framework repository. Use this when adding, updating, or running sample verification.

microsoft/agent-framework · 40 tokens

python-feature-lifecycle

Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.

microsoft/agent-framework · 43 tokens

build-and-test

How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.

microsoft/agent-framework · 26 tokens