Borrowing it
Nothing to install: this file belongs to 0xSoftBoi/suwappubot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/0xSoftBoi/suwappubot/main/.claude/skills/evolve/SKILL.mdgit clone --depth 1 https://github.com/0xSoftBoi/suwappubotWrote 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/0xsoftboi/suwappubot/evolve)<a href="https://agentmods.dev/skills/0xsoftboi/suwappubot/evolve"><img src="https://agentmods.dev/badge/skills/0xsoftboi/suwappubot/evolve.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 | $0.00077 | $0.00998 |
| Opus 5 | $0.00039 | $0.00499 |
| Sonnet 5 | $0.00015 | $0.00200 |
| Haiku 4.5 | $0.00008 | $0.00100 |
Grade A, and why
evolve 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/evolve — one self-improvement iteration
Design: docs/harness/self-improving.md (Hermes self-evolution + pi-reflect patterns). Loop shape: evaluate → reflect → patch → verify → commit. One iteration = ONE change. Small surgical diffs beat rewrites; the git log is the audit trail and the rollback mechanism.
1. Evaluate — read the evidence, never guess
python3 scripts/harness/journal_digest.py --days 30
git log --oneline -15 -- .claude/ CLAUDE.md
git log --oneline -- .claude/harness/lessons.md | head -20
Evidence sources, in priority order:
- Recurring error buckets in the digest (same failure across 2+ sessions).
- Recidivist lessons — a lessons.md section edited 3+ times means prose isn't working; it needs promotion to an enforcing artifact.
- Denial-heavy sessions — repeated permission prompts → allowlist candidates
for
.claude/settings.jsonpermissions. - User-stated friction if this run was invoked with a focus hint
(
/evolve <hint>— the hint outranks the digest).
If the digest is empty AND there's no hint and no recidivism: report "no signal, no change" and STOP. An evolution loop that edits without evidence is noise.
2. Reflect — pick ONE target and the right artifact type
Match the friction to the artifact that enforces the fix, preferring the most mechanical option (top = strongest):
| Friction pattern | Patch target |
|---|---|
| Model keeps doing a forbidden/broken thing | New or edited hook in .claude/hooks/ + settings.json |
| Multi-step procedure keeps going wrong | Skill in .claude/skills/<name>/SKILL.md |
| Wrong specialist/model routing | Agent def in .claude/agents/ or routing table in CLAUDE.md |
| Permission prompt friction | permissions.allow in .claude/settings.json |
| Repo fact the model keeps rediscovering | .claude/harness/lessons.md ## Facts |
| Judgment rule with no mechanical enforcement | CLAUDE.md (mind the 4000-word budget — merge, don't append) |
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 · 86 lines · 77 tokens per session scan A c195c2178396
evolve is a skill published in the GitHub repository 0xSoftBoi/suwappubot (3 stars, last pushed today), licensed Apache-2.0. It adds 77 tokens to every session and 998 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 2026-08-30.
Other skills, from other repositories
defi-protocols
DeFi protocol authority — flashloans, AMM design, lending markets, concentrated liquidity, MEV, triangular and cross-DEX arbitrage, stablecoin depeg dynamics, and on-chain capital routing across Uniswap V3, Aerodrome, Balancer, Curve, and Aave V3 on Ethereum, Base, Arbitrum, Optimism, and Polygon.
oneinch-aggregator
1inch DEX aggregator skill — swap tokens across 400+ DEXes, get quotes, check token approvals, Fusion+ cross-chain swaps, portfolio tracking. Requires API key from 1inch Developer Portal.
across-bridge
Bridge ETH and ERC-20 tokens across EVM chains via Across Protocol v3. One function for a quote, one function for the entire end-to-end bridge (approval + deposit + arrival verification). Use when the user wants to move tokens between chains (e.g. "bridge 50 USDC from Base to Arbitrum", "send ETH from Ethereum to…
ophis
Use this skill when the user asks to swap tokens, get a swap quote, check or cancel an order, or report the surplus their trades earned, via Ophis, the intent-based MEV-protected DEX aggregator. Triggers on phrases like "swap X for Y", "best price", "quote", "order status", "cancel my order", "how much surplus did I…
swap-via-ophis
Swap or bridge tokens through Ophis, an intent-based DEX aggregator. Parse a natural-language request, get a best-execution quote, build an EIP-712 order, sign it in the user's own wallet, and submit it. Non-custodial: the agent never holds keys or funds.
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.