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.
git clone --depth 1 https://github.com/Feynman520/d06-p01-self-improveWrote 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.
[](https://agentmods.dev/plugins/feynman520/d06-p01-self-improve/d06-p01-self-improve)<a href="https://agentmods.dev/plugins/feynman520/d06-p01-self-improve/d06-p01-self-improve"><img src="https://agentmods.dev/badge/plugins/feynman520/d06-p01-self-improve/d06-p01-self-improve/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/feynman520/d06-p01-self-improve/d06-p01-self-improve"><img src="https://agentmods.dev/badge/plugins/feynman520/d06-p01-self-improve/d06-p01-self-improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
self-improve 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 today.
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.
What it actually says
{
"name": "self-improve",
"version": "0.2.0",
"description": "Agent-neutral self-improvement loop: log correction moments, auto-apply rules on recurrence, grow skills and guarded scripts, mine session transcripts.",
"author": { "name": "Sejun Ham" }
}
What it installs
The manifest is a name and a version. 1 skill, 1 MCP server travel with it, and installing the plugin installs all of them — 46 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed 9678642b3e67
- 8d ago First seen · 7 lines scan A b7fbadbccc7f
self-improve is a plugin published in the GitHub repository Feynman520/d06-p01-self-improve (0 stars, last pushed yesterday), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
claude-smart
Self-improving Claude Code, Codex, and OpenCode plugin that turns corrections into Preferences, Project-specific skills, and Shared skills.
claude-video-vision
Give Claude the ability to watch and understand videos — extracts frames and audio for full video perception.
claude-patent-creator-standalone
Complete self-contained patent creation system - NO MCP server required. Uses Claude Code skills, agents, commands, and hooks.
toonify-mcp
Local context compression for Claude Code workflows, including structured data and debug-heavy output.
autosearch
Self-evolving deep research. Gets smarter every time you use it. Searches across channels, synthesizes cited reports, and learns which queries and platforms work best.
axme-code
(Alpha) Persistent memory, architectural decisions, and safety guardrails for Claude Code. Your agent starts every session with full project context — stack, decisions, patterns, safety rules, and a handoff from the previous session.