learn

learn is a command for coding agents from atuljha23/holocron. It costs 31 tokens per session (408 once invoked), scanned A, original, MIT.

A command that saves a durable lesson or correction in Holocron, a local SQLite-based store for remembered rules.

In plain words
What is it for?
Use it to record an imperative rule, its reason, tags, and whether it should apply to one project or to the user across projects.
Why use it?
It keeps useful guidance for future coding sessions instead of letting an important correction disappear after the current task.

Command

Part of the holocron plugin — 11 skills, 24 commands, 14 agents, 6 hooks shipped together

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 commands/atuljha23/holocron/learn
Clone the repo
git clone --depth 1 https://github.com/atuljha23/holocron

Or install holocron, the plugin that ships this one along with the rest of its 11 skills, 24 commands, 14 agents, 6 hooks.

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 learn

README.md
[![agentmods](https://agentmods.dev/badge/commands/atuljha23/holocron/learn.svg)](https://agentmods.dev/commands/atuljha23/holocron/learn)
Your own site
<a href="https://agentmods.dev/commands/atuljha23/holocron/learn"><img src="https://agentmods.dev/badge/commands/atuljha23/holocron/learn.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 408 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 $0.00031 $0.00408
Opus 5 $0.00015 $0.00204
Sonnet 5 $0.00006 $0.00082
Haiku 4.5 $0.00003 $0.00041

Measured 3d ago against content hash 68e1b827b49c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 3d 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.

commands/learn.md · 49 lines

What it actually says

/holocron:learn

Capture a rule that Claude should honor in future sessions.

If $ARGUMENTS is already a full invocation

Pass it through to the CLI:

node "${CLAUDE_PLUGIN_ROOT}/scripts/holocron-cli.js" add $ARGUMENTS

Otherwise, extract fields

If the user gave prose, extract:

  • title (short — 5–10 words — what this learning is about)
  • rule (the imperative — "always do X" / "never do Y")
  • reason (the "why" — usually ties to an incident, preference, or architectural constraint)
  • tags (comma-separated — e.g. testing,db, frontend,a11y, security)
  • scope (user by default — follows you across projects; project — lives in this repo's .holocron/)

Then run:

node "${CLAUDE_PLUGIN_ROOT}/scripts/holocron-cli.js" add \
  --title "<title>" \
  --rule "<rule>" \
  --reason "<reason>" \
  --tags "<tags>" \
  --scope <scope>

Rules for what to save

Save when the correction is durable — a rule that should apply to future work. Do NOT save:

  • One-off debugging details
  • Current-task scratch state
  • Things the code already enforces

See also: /holocron:recall <query> to search, /holocron:list to browse.

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. 3d ago First seen · 49 lines · 0 tokens per session scan A 68e1b827b49c

Subscribe to this mod's changes

learn is a command published in the GitHub repository atuljha23/holocron (2 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 408 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.