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 SELAT-AI/selat-skills --skill self-evolving-agentgit clone --depth 1 https://github.com/SELAT-AI/selat-skillsWrote 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/selat-ai/selat-skills/self-evolving-agent)<a href="https://agentmods.dev/skills/selat-ai/selat-skills/self-evolving-agent"><img src="https://agentmods.dev/badge/skills/selat-ai/selat-skills/self-evolving-agent/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/skills/selat-ai/selat-skills/self-evolving-agent"><img src="https://agentmods.dev/badge/skills/selat-ai/selat-skills/self-evolving-agent.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00089 | $0.02579 |
| Opus 5 | $0.00044 | $0.01290 |
| Sonnet 5 | $0.00018 | $0.00516 |
| Haiku 4.5 | $0.00009 | $0.00258 |
Grade A, and why
self-evolving-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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
self-evolving-agent
Design and operate a budgeted economic agent: an agent given a fixed budget and its own operational identity. The agent can provision an AgentMail address, use that address to authenticate its Circle Agent Wallet, acquire infrastructure, gather social and financial intelligence, produce monetizable insight or trading hypotheses, and use realized profits to sustain expenses.
This skill treats "self-evolving" as economic adaptation under constraints. The agent evolves by reallocating budget toward tools, data sources, strategies, and products that improve verified net returns. It does not assume profitability, does not bypass regulatory or exchange constraints, and does not make live trades without explicit user-approved risk limits.
When To Use
Use this skill when the user asks to:
- build an autonomous or semi-autonomous economic agent;
- give an agent its own email address and agent-wallet treasury;
- use an agent-owned mailbox to receive OTPs for the agent's own Circle wallet;
- give an agent a budget and have it buy compute, hosting, domains, or paid data;
- gather social intelligence, financial intelligence, or market signals;
- test whether intelligence can be monetized through subscriptions, reports, lead generation, trading, or prediction-market research;
- define a reinvestment loop where profits sustain operating expenses;
- add treasury, runway, P&L, risk, and shutdown rules to an agent.
Do not use this skill to provide personalized financial advice, promise profits, evade platform rules, trade on inside information, manipulate markets, retrieve OTPs from a human's mailbox, or move funds without explicit approval.
Operating Definition
A self-evolving economic agent follows this loop:
identity -> agent wallet -> budget -> acquire infrastructure
-> gather intelligence -> form hypotheses -> monetize or paper-trade
-> measure P&L -> reinvest, pause, or shut down
The agent is successful only if realized revenue or trading profits exceed:
What ships with it
9 files beside SKILL.md 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.
- evals/evals.json 2.6 KB
- manifest.json 1.7 KB
- references/catalogue-findings.md 3.3 KB
- references/clawhub-patterns.md 1.4 KB
- references/economic-model.md 2.8 KB
- references/endpoints.md 2.9 KB
- references/identity-wallet-bootstrap.md 3.1 KB
- references/risk-policy.md 3.4 KB
- references/verification.md 1.3 KB
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.
- 10d ago First seen · 258 lines · 89 tokens per session scan A 5042218907d8
self-evolving-agent is a skill published in the GitHub repository SELAT-AI/selat-skills (2 stars, last pushed today), licensed Apache-2.0. It adds 89 tokens to every session and 2,579 once invoked, about $0.0004 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.
Other skills, from other repositories
selat-capabilities-for-metamask
SELAT's capability layer for agents on a MetaMask Agent Wallet — tool use beyond the agent's native abilities, paid per call. Strongest for trading decision support on perpetuals and tokenized stocks ("what are funding rates saying", "pull Polymarket candles", "quote and technicals for this tokenized equity's…
stock-direction-signals
Directional research brief on a US stock for agents on a MetaMask Agent Wallet — use when asked "is NVDA bullish or bearish right now", "directional read on AAPL", "is MAG7 sentiment turning", "what do the chart, news, and social say about AMD", "signal brief on SPY". Nine paid reads — quote, daily chart, RSI, MACD…
vc-ai-infra-scout
Deal-sourcing scout for VCs running an AI-infrastructure thesis — AI infra, crypto-AI/decentralized-AI, robotics/embodied-AI, agentic payments. Use when asked to "scout AI infra startups", "find founders who haven't raised yet", "build a deal shortlist for my thesis", or "what pre-seed/seed rounds are being announced…
internet-court
Entry point for Internet Court — the trust layer for agent-to-agent commerce. Use whenever an agent needs to transact with another agent or a paid service, or a user mentions agent payments, paid APIs (HTTP 402/x402), wallet custody or trust concerns, spending mandates, delegated permissions (ERC-7710/7715), escrow…
okx-agent-payments-protocol
Use when an agent hits HTTP 402 / payment-required, or the user mentions x402, x402Version, X-PAYMENT, PAYMENT-REQUIRED, PAYMENT-SIGNATURE, WWW-Authenticate: Payment, permit2, upto, metered billing, a payment channel / voucher / session, channelId / channelid, opening / closing / topping up / settling / refunding a…
okx-dapp-discovery
Plugin router for 20 third-party DeFi protocols (Polymarket, Aave, Hyperliquid, PancakeSwap, Morpho, Raydium, Curve, Compound, Pendle, Lido, ether.fi, GMX, Kamino, Orca, Meteora, Clanker, pump.fun, Uniswap) and their protocol-native tokens (HYPE, HLP, eETH, weETH, stETH, wstETH, LDO, GHO, CAKE, CRV, COMP, RAY, ETHFI…