continuous-learning

continuous-learning is a skill for Claude Code, Codex from a5c-ai/babysitter. It costs 25 tokens per session (456 once invoked), scanned A, original, MIT.

A workflow that learns reusable development practices from code changes, decisions, errors, and tool usage, then turns well-tested patterns into versioned agent skills.

In plain words
What is it for?
Use it to extract conventions and architectural decisions, score their usefulness, create SKILL.md instructions, organise dependencies, and export portable skill bundles.
Why use it?
It removes the need to repeatedly rediscover successful approaches across projects. Confidence and reliability checks help filter out patterns that are not broadly useful.

Skill for Claude CodeCodex

About the project

Babysitter is a workflow engine for AI coding agents that enforces predefined steps, quality checks, human approvals, and decision records. It is used to coordinate complex, repeatable agent workflows across supported coding tools. The catalogue contains skills, agents, instructions, settings, a plugin, and an MCP integration for its workflow.

a5c-ai/babysitter · 1,765 stars · on GitHub

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/a5c-ai/babysitter/continuous-learning
Any agent
npx skills add a5c-ai/babysitter --skill continuous-learning
Clone the repo
git clone --depth 1 https://github.com/a5c-ai/babysitter

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 continuous-learning

README.md
[![agentmods](https://agentmods.dev/badge/skills/a5c-ai/babysitter/continuous-learning.svg)](https://agentmods.dev/skills/a5c-ai/babysitter/continuous-learning)
Your own site
<a href="https://agentmods.dev/skills/a5c-ai/babysitter/continuous-learning"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/continuous-learning.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 456 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 $0.00025 $0.00456
Opus 5 $0.00013 $0.00228
Sonnet 5 $0.00005 $0.00091
Haiku 4.5 $0.00003 $0.00046

Measured yesterday against content hash c3def4da77c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

continuous-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 yesterday.

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.

library/methodologies/everything-claude-code/skills/continuous-learning/SKILL.md · 64 lines

What it actually says

  • Analyze code changes and implementation approaches
  • Identify recurring patterns and conventions
  • Extract architectural decisions with rationale
  • Capture error resolution strategies
  • Record tool usage patterns
  • Assign initial confidence scores (0-100)

2. Pattern Evaluation

  • Score generalizability (0-100): cross-project applicability
  • Score reliability (0-100): validation frequency
  • Score impact (0-100): outcome improvement
  • Composite: generalizability * 0.3 + reliability * 0.4 + impact * 0.3
  • Filter below confidence threshold (default: 75)
  • Merge similar patterns

3. Skill Creation

  • Convert high-confidence patterns to SKILL.md format
  • Write clear instructions with phases
  • Include when-to-use and when-not-to-use sections
  • Add usage examples and agent references
  • Follow kebab-case naming convention

4. Organization

  • Categorize: language-specific, domain, business, meta
  • Resolve naming conflicts
  • Update indexes and manifests
  • Create dependency graphs

5. Version and Export

  • Assign semantic versions by maturity
  • Create portable export bundles
  • Include usage examples and test cases
  • Generate import instructions

Strategic Compaction

  • Analyze context token usage
  • Identify low-value context for compression
  • Archive completed phases to memory files
  • Calculate token savings per suggestion

When to Use

  • End of development sessions
  • After significant code reviews
  • After debugging sessions
  • Periodically during long sessions

Agents Used

  • continuous-learning (custom agent for this skill)
  • context-engineering (compaction analysis)
Files

What ships with it

1 file 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. yesterday First seen · 64 lines · 25 tokens per session scan A c3def4da77c8

Subscribe to this mod's changes

continuous-learning is a skill published in the GitHub repository a5c-ai/babysitter (1,765 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 456 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

writing-prose

Prose quality methodology for writing and assessing documentation. Grounded in plain language and ASD-STE100 Simplified Technical English in two modes — strict for instruction text, STE-flavored for descriptive prose.

bostonaholic/team · 44 tokens

goga-discover

Interview the user relentlessly about a decision until every branch of the design tree is resolved, then record the result as a short ADR.

qarium/goga · 31 tokens

explain

코드를 비유 기반으로 설명하고 Mermaid 다이어그램을 생성합니다. 파일/기능/줌아웃 3가지 모드 지원. /explain @file.ts (상세 설명), /explain "로그인 기능" (기능 단위), /explain --zoom-out @file.ts (한 단계 위 맵).

Dannykkh/skill-olympus · 76 tokens

how

Explain how a subsystem, feature flow, or code path works, at the level a senior engineer onboarding onto it needs: architecture, runtime flow, where things live, and the gotchas. Simple questions are answered inline; complex ones fan out parallel read-only explorers and synthesize their traces into one coherent…

bostonaholic/team · 128 tokens

java-optionals-eval-capture

Use in Symphony for Trello when a Java change or review presents a reusable Optional or absence/fallback strategy-selection lesson, including on an adjacent owning API such as ScopedValue even when no java.util.Optional appears. Capture the before/prompt/after code and create or update a self-contained eval issue in…

martin-francois/symphony-trello · 78 tokens

java-streams-eval-capture

Use in Symphony for Trello when a Java change or review presents a reusable lesson about choosing or preserving a stream, collector, direct result-producing collection transformation, or character-predicate traversal, including identity or delimited string reductions, even when the preferred final code contains no…

martin-francois/symphony-trello · 91 tokens