teach

A command for manually saving a lesson in the project's memory system as a high-confidence learning note. The lesson is tagged and associated with the current project directory.

In plain words
What is it for?
Use it to record a deliberate lesson about the project, such as a design decision or recurring issue. The memory can then be surfaced when the relevant project is edited.
Why use it?
Useful knowledge can be lost after a coding session if it is not recorded. This command preserves a lesson so later work can retrieve it.

Command

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/rasputinkaiser/self-improvement-plugin/teach
Clone the repo
git clone --depth 1 https://github.com/RasputinKaiser/Self-Improvement-Plugin
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 216 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 $0.00020 $0.00216
Opus 5 $0.00010 $0.00108
Sonnet 5 $0.00004 $0.00043
Haiku 4.5 $0.00002 $0.00022

Measured 2d ago against content hash 9e15d746ed12, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

teach 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 2d 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/teach.md · 20 lines

What it actually says

Argument: $ARGUMENTS — the lesson text.

Record a deliberate, hand-written lesson (as opposed to one auto-captured from a transcript). These are the highest-signal records because a human/agent chose to write them down.

Write it scoped to the current working directory: python3 <mf_cli> record --tier learning --title "taught lesson: <short topic>" \ --body "$ARGUMENTS" --tags lesson,taught,manual --scope "$CWD" \ --provenance-type source_backed_agent_run --confidence high --status active

(The memory_fabric CLI path is resolved the same way the other scripts resolve it — see scripts/memory_fabric_preflight.py for the lookup.)

Confirm with: RECORDED: <record_id> and remind that it will surface via memory_fabric_preflight the next time the touched scope is edited.

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. 2d ago First seen · 20 lines · 20 tokens per session scan A 9e15d746ed12

Subscribe to this mod's changes

teach is a command published in the GitHub repository RasputinKaiser/Self-Improvement-Plugin (6 stars, last pushed 5d ago), licensed MIT. It adds 20 tokens to every session and 216 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 2026-08-31.