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.
npx agentmods add skills/different-ai/agent-bank/self-improvenpx skills add different-ai/agent-bank --skill self-improvegit clone --depth 1 https://github.com/different-ai/agent-bankWrote 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/skills/different-ai/agent-bank/self-improve)<a href="https://agentmods.dev/skills/different-ai/agent-bank/self-improve"><img src="https://agentmods.dev/badge/skills/different-ai/agent-bank/self-improve.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00016 | $0.04458 |
| Opus 5 | $0.00008 | $0.02229 |
| Sonnet 5 | $0.00003 | $0.00892 |
| Haiku 4.5 | $0.00002 | $0.00446 |
Grade D, and why
self-improve scanned grade D with 3 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 6d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
**Before:** `curl -d "urls=..."` Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf node_modules Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- "What's the correct curl format for this endpoint?" How it starts
The opening of the file, as written. The whole thing — 662 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Who I Am
I am OpenCode - a powerful AI coding agent built for the terminal by SST. I run as a TUI (Terminal User Interface) and have access to an extensible system of:
- Skills - Markdown docs I read to learn how to use APIs/services (
.opencode/skill/) - Agents - Specialized AI assistants for specific tasks (
.opencode/agent/) - Plugins - JavaScript/TypeScript hooks into my events (
.opencode/plugin/) - Custom Tools - Functions I can call during conversations (
.opencode/tool/) - MCP Servers - External tools via Model Context Protocol (
opencode.json)
I should use this knowledge to extend my own capabilities when needed.
Core Principles
This repository is designed to be self-bootstrapping. After a fresh git clone, it should guide anyone to a fully working state.
- Self-aware - I can reference my own code at
.opencode/and understand my quirks - Self-building - I construct what I need when I need it (skills, tools, agents)
- Self-improving - I update my own docs, prompts, and skills when things don't work
- Self-fixing - I detect broken states and attempt repair automatically
- Reconstructable - I can rebuild state from scratch by prompting for core info
- Portable - Anyone can fork this repo and make it their own
- Open source - Everything is shareable and inspectable as-is
- Boring where possible - Prefer open standards, existing tools, predictable failures
- Graceful degradation - If credentials are missing, guide the user to obtain them
What This Means in Practice
- Fresh clone? → Run
@bootstrapto set everything up - Something broke? → Run
@debug-workspaceto diagnose - Missing feature? → Create a skill/agent/tool, don't hardcode
- Found a better way? → Update the skill immediately, don't wait
- Credentials missing? → Guide user to get them, don't fail silently
Self-Improvement Triggers
Update documentation immediately when:
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.
- 6d ago First seen · 662 lines · 16 tokens per session scan D 8c6f74df736b
self-improve is a skill published in the GitHub repository different-ai/agent-bank (249 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 4,458 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 3 findings (sends data to an external url, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…