self-improvement

A command that reviews pending learning notes from this machine and promotes useful recurring lessons through a review pipeline.

In plain words
What is it for?
Running an immediate, visible review of pending learnings, errors, and feature requests.
Why use it?
It checks that the required review agents exist before processing learnings, reducing the chance of running an incomplete setup.

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/trtmn/agent-plugins/self-improvement
Clone the repo
git clone --depth 1 https://github.com/trtmn/agent-plugins
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 427 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 $0.00000 $0.00427
Opus 5 $0.00000 $0.00214
Sonnet 5 $0.00000 $0.00085
Haiku 4.5 $0.00000 $0.00043

Measured 2d ago against content hash d42ca33fbdc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

self-improvement 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.

plugins/self-improvement/commands/self-improvement.md · 17 lines

What it actually says

Run the self-improvement review pipeline now, in the foreground, against this machine's pending learnings.

First, check that ~/.claude/agents/learnings.md and ~/.claude/agents/learning-investigator.md exist. If either is missing, stop and tell me: "⚠ The self-improvement agents aren't wired up. Run /self-improvement:setup first." Do not proceed without them.

Then delegate to the self-improvement subagent via the Agent tool (subagent_type: self-improvement). Run it in the foreground so I can watch promotions happen live and interrupt if needed. Do NOT pass a transcript path (this is a mid-session manual run, not a session-end sweep) unless I explicitly ask you to sweep this conversation.

The subagent runs the same non-interactive pipeline the autonomous session-end hook uses:

  1. (Optional, only if I ask) sweep this conversation for anything capture missed.
  2. Read pending entries from ~/.learnings/{LEARNINGS,ERRORS,FEATURE_REQUESTS}.md — and, since this is a manual run inside a repo, the project-level .learnings/ mirror too.
  3. Dispatch a learning-investigator per candidate to judge needed-ness (conservative bar: high confidence + a recurrence signal + not a duplicate).
  4. Auto-promote the qualifiers — append to the target CLAUDE.md, log a [PROMO-<hex>] to ~/.learnings/CHANGELOG.md, remove from the pending file. Skip clear rejects with a [SKIP-<hex>]. Leave uncertain entries pending.
  5. Report a summary: swept / promoted / skipped / left-pending, with targets.

This run auto-promotes (no per-item approval prompt) — that's intentional and matches the autonomous behavior. Everything is logged; undo any promotion with /self-improvement:revert <PROMO-hex>.

For raw autonomous capture (the passive side), use the separate learnings subagent — not this one.

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 · 17 lines · 0 tokens per session scan A d42ca33fbdc3

Subscribe to this mod's changes

self-improvement is a command published in the GitHub repository trtmn/agent-plugins (2 stars, last pushed 5d ago), licensed Unlicense. It costs nothing until one of its globs matches a file; then it loads 427 tokens. 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.