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 skills add Mangi-11/Eta --skill self-improving-agentgit clone --depth 1 https://github.com/Mangi-11/EtaWrote 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/mangi-11/eta/self-improving-agent)<a href="https://agentmods.dev/skills/mangi-11/eta/self-improving-agent"><img src="https://agentmods.dev/badge/skills/mangi-11/eta/self-improving-agent.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00033 | $0.00501 |
| Opus 5 | $0.00016 | $0.00251 |
| Sonnet 5 | $0.00007 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
self-improving-agent 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 8d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 8d ago First seen · 62 lines · 33 tokens per session scan A d4b39a6fdefe
self-improving-agent is a skill published in the GitHub repository Mangi-11/Eta (1,324 stars, last pushed yesterday), with no licence file. It adds 33 tokens to every session and 501 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 2026-08-30.
Other skills, from other repositories
memory
Expertise in maintaining persistent bot memory, synchronizing with previous sessions via the Task Ledger, and preserving decision logs.
collaboration-intelligence
Maintain and use a cross-channel collaboration map of rooms, people, agents, agent owners, relationships, expertise, ownership, roster, priority/VIP handling, and recent context. Trigger when a task or message carries room/channel/sender/member metadata; the user asks who is in a room, what it is for, who owns or…
context-drop
Tiny Swift CLI that reads the focused app's text selection via the macOS Accessibility API. Sutando.app's "drop context" action (hotkey configurable via state/hotkeys.json) shells out to this binary to capture what you have highlighted.
context-reconstruct
Re-anchor on the durable record (current-track, live owner thread, pending-questions, relay, buildlog) before acting on anything that depends on earlier context. Read, do not recall.
session-recap
Reconstruct what happened in a past core session — from a high-level summary down to verbatim owner quotes — by reading the raw session transcripts (complete, crash-proof, unbiased), not the curated relay/handoff notes.
duduclaw-platform
Use the DuDuClaw MCP tools (persistent memory, shared wiki, task board, channel messaging) when the user asks to remember something across sessions, share knowledge with their team's AI employees, manage tasks, or message someone on LINE/Telegram/Discord/Slack. Requires a running DuDuClaw gateway (npx duduclaw onboard…