continuous-learning

continuous-learning is a skill for Claude Code from ShaheerKhawaja/ProductionOS. It costs 36 tokens per session (749 once invoked), scanned A, original, MIT.

A session-learning system that watches coding-agent activity, finds repeated patterns, and records them as reusable notes called instincts.

In plain words
What is it for?
It helps capture working habits, track evidence for those habits, rate confidence in them, and suggest or apply them in later coding sessions.
Why use it?
It reduces the need to repeat the same guidance across sessions and projects by remembering patterns that proved useful. Patterns start local and can be shared more widely when they occur often enough.

Skill for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: mentions CLAUDE.md.

Part of the productionos plugin — 4 skills, 41 commands, 11 agents shipped together

Good fit It helps capture working habits, track evidence for those habits, rate confidence in them, and suggest or apply them in later coding sessions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shaheerkhawaja/productionos/continuous-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 ShaheerKhawaja/ProductionOS --skill continuous-learning
Clone the repo
git clone --depth 1 https://github.com/ShaheerKhawaja/ProductionOS

Made for: Claude Code.

Or install productionos, the plugin that ships this one along with the rest of its 4 skills, 41 commands, 11 agents.

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/shaheerkhawaja/productionos/continuous-learning.svg)](https://agentmods.dev/skills/shaheerkhawaja/productionos/continuous-learning)
Your own site
<a href="https://agentmods.dev/skills/shaheerkhawaja/productionos/continuous-learning"><img src="https://agentmods.dev/badge/skills/shaheerkhawaja/productionos/continuous-learning.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 749 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 $0.00036 $0.00749
Opus 5 $0.00018 $0.00375
Sonnet 5 $0.00007 $0.00150
Haiku 4.5 $0.00004 $0.00075

Measured 7d ago against content hash f78899a72ab4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 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.

.claude/skills/continuous-learning/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ProductionOS Continuous Learning

Architecture

SESSION ACTIVITY (via PostToolUse hooks)
       ↓
  Observation Log (~/.productionos/analytics/skill-usage.jsonl)
       ↓
  Pattern Extractor (runs at session end via Stop hook)
       ↓
  Instinct Creation (~/.productionos/instincts/project/{hash}/)
       ↓
  Confidence Scoring (0.0 - 1.0, based on repetition + outcome)
       ↓
  Auto-Promotion (confidence > 0.8 → global instinct)
       ↓
  Global Instincts (~/.productionos/instincts/global/)

Instinct Format

Each instinct is a single markdown file:

---
name: {pattern-name}
confidence: 0.65
observations: 3
first_seen: 2026-03-20
last_seen: 2026-03-20
scope: project
promoted_from: null
---

## Pattern
{What was observed}

## Evidence
- Session {date}: {observation 1}
- Session {date}: {observation 2}

## Application
{When to apply this pattern in future sessions}

Confidence Scoring

Confidence Meaning Action
0.0 - 0.3 Weak signal Store but don't act
0.3 - 0.6 Emerging pattern Suggest when relevant
0.6 - 0.8 Strong pattern Apply proactively
0.8 - 1.0 Proven pattern Auto-promote to global

Observation Types

  1. Code Pattern — Repeated code structure across sessions
  2. Tool Usage — Preferred tool sequences (e.g., always Grep before Edit)
  3. Error Recovery — How errors were resolved (reusable fix patterns)
  4. Architecture Decision — Repeated structural choices
  5. Review Finding — Common issues found in code reviews

Stop Hook: Pattern Extraction

At session end, the Stop hook:

  1. Reads ~/.productionos/analytics/skill-usage.jsonl for this session
  2. Groups events by type (edit, bash, security_edit, etc.)
  3. Identifies patterns (repeated file types, common commands, recurring errors)
  4. Creates or updates instinct files
  5. Bumps confidence on existing instincts that match

Commands

  • pos-instincts list — Show all instincts with confidence
  • pos-instincts promote {name} — Manually promote to global
  • pos-instincts demote {name} — Reduce confidence
  • pos-instincts forget {name} — Delete an instinct

Read the full file on GitHub · 100 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 · 100 lines · 36 tokens per session scan A f78899a72ab4

Subscribe to this mod's changes

continuous-learning is a skill published in the GitHub repository ShaheerKhawaja/ProductionOS (8 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 749 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 2026-08-31.

Related

Other skills, from other repositories

lembas

Use between workflow phases or when context feels bloated. Writes a structured checkpoint capturing task, findings, files, state, and next steps, then continues from that summary instead of the full history. Invoke standalone or automatically between quest phases.

justinjdev/fellowship · 51 tokens

fellowship

Multi-task orchestrator. Coordinates agent teammates (led by Gandalf) running /quest (code) or /scout (research) workflows. Use when you have multiple independent tasks to run in parallel.

justinjdev/fellowship · 45 tokens

quest

Use for multi-file or multi-step changes that need research and a plan — not single-file fixes under 50 lines that follow an existing pattern (see Escape Hatch below). Runs the Research → Plan → Implement → Review lifecycle with a hard gate leaving each of the first three phases and context compaction between them.

justinjdev/fellowship · 64 tokens

compress

Prompt-Studio memory compressor. Shrinks CLAUDE.md, todo lists, and preference files into Prompt-Studio's lean format to cut input tokens on every load. Preserves all technical substance, code, URLs, and structure. Compressed output overwrites the original; human-readable backup stored out-of-tree as FILE.original.md…

utk2103/Prompt-Studio · 98 tokens

retro

Invoke after a fellowship disbands, or when the user explicitly asks for a retrospective. Collects gate history, palantir alerts, and quest metrics to surface patterns and interactively recommend configuration improvements.

justinjdev/fellowship · 42 tokens

missive

Invoke only when spawning a quest from a GitHub issue reference. Fetches GitHub issue context for quest spawning. Parses issue references, retrieves structured data via gh, and produces branch suggestions and PR keywords. Used standalone or as input to quest orchestration.

justinjdev/fellowship · 54 tokens