capture-learning

capture-learning is a skill for Claude Code, Codex from Kastalien-Research/thoughtbox. It costs 23 tokens per session (321 once invoked), scanned A, original, MIT.

A session tool for recording important lessons from coding work and saving them as structured notes for future sessions. It records the problem, solution, reusable pattern, related files, and freshness.

In plain words
What is it for?
Use it after solving a difficult problem to capture project rules, debugging insights, and agent-specific patterns.
Why use it?
It turns one-off discoveries and failed approaches into reference material that can guide later work.

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/kastalien-research/thoughtbox/capture-learning
Any agent
npx skills add Kastalien-Research/thoughtbox --skill capture-learning
Clone the repo
git clone --depth 1 https://github.com/Kastalien-Research/thoughtbox

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 capture-learning

README.md
[![agentmods](https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/capture-learning.svg)](https://agentmods.dev/skills/kastalien-research/thoughtbox/capture-learning)
Your own site
<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/capture-learning"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/capture-learning.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 321 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 $0.00023 $0.00321
Opus 5 $0.00012 $0.00161
Sonnet 5 $0.00005 $0.00064
Haiku 4.5 $0.00002 $0.00032

Measured 4d ago against content hash 2de78d7638e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

capture-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 4d 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.

.agents/skills/capture-learning/SKILL.md · 44 lines

What it actually says

Reflect on the current session and capture learnings. Context: $ARGUMENTS

Process

1. Reflect

  • What was the main problem being solved?
  • What non-obvious insights emerged?
  • What patterns are reusable in future work?
  • What failed and why?

2. Structure the Learning

Format each learning as:

### [Date]: [Title]
- **Issue**: [The problem encountered]
- **Solution**: [What worked]
- **Pattern**: [The reusable principle extracted]
- **Files**: [Key file references, if applicable]
- **Freshness**: HOT (actively relevant) | WARM (occasionally relevant) | COLD (reference only)

3. Store

Write the learning to the appropriate location:

  • Agent-specific patterns: Update the relevant agent's project memory
  • Project-wide rules: Add to .Codex/rules/ as a new file or append to an existing one
  • Debugging insights: Add to auto-memory MEMORY.md

4. Calibrate

Check existing learnings for staleness:

  • Are any HOT items now WARM or COLD?
  • Are any previous learnings contradicted by what we learned today?
  • Remove or update anything that's no longer accurate.
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. 4d ago First seen · 44 lines · 23 tokens per session scan A 2de78d7638e7

Subscribe to this mod's changes

capture-learning is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 321 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 2026-08-30.

Related

Other skills, from other repositories

forget

Delete specific observations from agentmemory after showing them and getting explicit confirmation. Use when the user says "forget this", "delete memory", "remove that note", or wants to scrub specific data for privacy.

rohitg00/agentmemory · 43 tokens

handoff

Resume the most recent agent session for the current working directory, leading with any unanswered question. Use when the user says "where were we", "resume", "handoff", "pick up where I left off", or starts a session with no fresh context.

rohitg00/agentmemory · 55 tokens

memory-discipline

The session loop that makes agentmemory pay off, recall before starting work, save at decision points, learn from corrections. Use when starting a nontrivial task, after settling a decision or debugging a gotcha, or whenever deciding if something belongs in memory.

rohitg00/agentmemory · 56 tokens

agentmemory-hooks

The agentmemory plugin hooks that capture observations automatically across the agent session lifecycle. Use when explaining how memory gets captured without manual saves, when debugging missing observations, or when tuning what gets recorded.

rohitg00/agentmemory · 42 tokens

session-history

Show what happened in recent past sessions on this project as a clean timeline. Use when the user asks "what did we do last time", "session history", "past sessions", or wants an overview of previous work.

rohitg00/agentmemory · 47 tokens

agentmemory-agents

How agentmemory wires into host coding agents via the connect command. Use when installing agentmemory into a specific agent, when asked which agents are supported, or when a connect adapter writes the wrong config path.

rohitg00/agentmemory · 46 tokens