save-learning

save-learning is a skill for Claude Code, Codex from HumanDealer/vibeproof. It costs 34 tokens per session (518 once invoked), scanned A, original, MIT.

A process for saving durable decisions, lessons, and useful references in a memory wiki so they can be reused later.

In plain words
What is it for?
It determines whether an insight is worth keeping, classifies it, and writes a dated Markdown page with a description, confidence level, and tags.
Why use it?
It prevents important, non-obvious knowledge from being forgotten and relearned after bugs, incidents, or difficult decisions.

Skill for Claude CodeCodex

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

Good fit It determines whether an insight is worth keeping, classifies it, and writes a dated Markdown page with a description, confidence level, and tags.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/humandealer/vibeproof/save-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 HumanDealer/vibeproof --skill save-learning
Clone the repo
git clone --depth 1 https://github.com/HumanDealer/vibeproof

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 save-learning

README.md
[![agentmods](https://agentmods.dev/badge/skills/humandealer/vibeproof/save-learning.svg)](https://agentmods.dev/skills/humandealer/vibeproof/save-learning)
Your own site
<a href="https://agentmods.dev/skills/humandealer/vibeproof/save-learning"><img src="https://agentmods.dev/badge/skills/humandealer/vibeproof/save-learning.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 518 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 $0.00034 $0.00518
Opus 5 $0.00017 $0.00259
Sonnet 5 $0.00007 $0.00104
Haiku 4.5 $0.00003 $0.00052

Measured 8d ago against content hash 264888ffc3b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

save-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 8d 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.

skills/save-learning/SKILL.md · 60 lines

What it actually says

Save a Learning

Turn a one-time insight into permanent, reusable knowledge. Without this, agents are amnesiac — they re-learn and re-break the same things forever.

When to use

  • A non-obvious decision was made (and why, and the alternatives).
  • A lesson was learned the hard way (a bug, an incident, a surprise).
  • A useful reference surfaced (an external system, doc, dashboard).
  • The human says "remember this", "save that", "don't forget".

Before you save — the filter

Ask: is this surprising or non-obvious?

  • ✅ Save: "Vendor's weekend data is unreliable until D+3" — non-obvious, costly to relearn.
  • ❌ Don't save: "the auth code is in auth.py" — read the code instead.
  • ❌ Don't save: secrets, personal data, ephemeral session state.

If it's derivable from the code, git history, or the docs — don't save it.

Steps

  1. Pick the type: decision · lesson · reference · person (rules/memory-system.md).

  2. Write the page at memory/wiki/<type>/<slug>.md with frontmatter:

    ---
    name: <title>
    description: <one line — how you'd recognize this is relevant later>
    type: lesson
    created: <date>
    confidence: HIGH | MED | LOW
    tags: [<topic>]
    ---
    

    Body: what it is, why it matters, what to do about it. Keep it short.

  3. Run the privacy filter — strip any secret / personal data before saving.

  4. Add one line to memory/INDEX.md pointing at the new page.

  5. Append one line to memory/log.md: ## [<date> <time>] <type> | <summary> | <path>

  6. If this supersedes an older fact, link them both ways and banner the old page (rules/memory-system.md) — don't silently delete.

Result

Next session, the agent reads the index, sees the lesson, and doesn't repeat the mistake. That's the compounding.

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. 8d ago First seen · 60 lines · 34 tokens per session scan A 264888ffc3b5

Subscribe to this mod's changes

save-learning is a skill published in the GitHub repository HumanDealer/vibeproof (2 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 518 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

continual-learning

Orchestrate continual learning by delegating transcript mining to agents-memory-updater and writing durable memory to local JSON (never root AGENTS.md Learned sections). USE WHEN continual learning, mine prior chats, maintain agent memory, or the stop hook triggers this skill.

docxology/template · 56 tokens

context-engineering

Ensure graphify corpus is current and complete before each agent session. Define minimum AI-accessible documentation per repo. Use at session startup to verify internal context is available to AI tools. Implements DORA AI Capability 3.

paruff/uFawkesAI · 48 tokens

learn

Review the current conversation and update project knowledge artifacts - common-gotchas.md (bug patterns), AGENTS.md (conventions), agent memory (cross-session). Use when asked to '/learn', 'what did we learn', 'capture lessons', 'update common-gotchas'.

craigcossairt/trellis · 58 tokens

llm-wiki

Maintain a personal team knowledge base using the LLM Wiki pattern — incremental ingest, query, and lint operations on a layered wiki architecture.

TheSmuks/ai-project-template · 31 tokens

checkpoint

Save all work, update memory, commit, push, and prepare to end the session. Use when user says "save my work", "wrap up", or "I'm done for now". Use at natural breakpoints or when context is getting large.

john-wilmes/claude-agentic-coding-playbook · 52 tokens

learn

Capture a lesson as a structured knowledge entry. Use when you discover a non-obvious bug, workaround, or pattern worth preserving for future sessions. Use when user says "remember this", "save this lesson", or "this is worth noting".

john-wilmes/claude-agentic-coding-playbook · 51 tokens