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/stealthy-mcstealth/self-evolve/improve-urselfnpx skills add Stealthy-McStealth/self-evolve --skill improve-urselfgit clone --depth 1 https://github.com/Stealthy-McStealth/self-evolveWrote 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/stealthy-mcstealth/self-evolve/improve-urself)<a href="https://agentmods.dev/skills/stealthy-mcstealth/self-evolve/improve-urself"><img src="https://agentmods.dev/badge/skills/stealthy-mcstealth/self-evolve/improve-urself.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 | $0.00132 | $0.00805 |
| Opus 5 | $0.00066 | $0.00402 |
| Sonnet 5 | $0.00026 | $0.00161 |
| Haiku 4.5 | $0.00013 | $0.00081 |
Grade A, and why
improve-urself 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 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.
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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
improve-urself
This skill extracts durable learnings from the current conversation and creates or updates skills so the pattern persists beyond this session.
The core idea: you just ran an experiment. The conversation is the execution trace. Mine it.
Step 1: Mine the conversation for signal
Scan the conversation for:
- Mistakes made — Claude produced wrong output, used the wrong tool, misread intent
- Corrections given — user said "no, do it like this", "you should have", "next time"
- Patterns that worked — a technique that solved something cleanly, a format the user liked
- Repeated friction — anything the user had to clarify more than once
- Domain-specific knowledge — facts, conventions, or constraints specific to this project/codebase
If called with topic args (e.g., /improve-urself bash errors), focus extraction on
those topics. Otherwise extract the 1–3 most impactful learnings from the whole session.
For each learning, note:
- What happened (the failure or insight)
- What the correct behavior is
- How generalizable it is (just this project? all projects? this type of task?)
Step 2: Check for existing skills to update
Look in the skills/ directory of this plugin for existing skills with overlapping scope.
Also check any loaded skills in the current session.
If a skill already covers the topic:
- Propose an edit to that skill rather than creating a new one
- Merging is better than fragmentation — don't create a separate skill for every correction if they belong together
If no existing skill covers it, proceed to create a new one.
Step 3: Draft the skill content
Use the format in references/skill-standards.md. Key principles:
- Be specific, not vague. "When running bash commands that might fail, always check exit codes and print stderr" is useful. "Be careful with bash" is not.
- Include the why. Explain the failure mode being prevented, not just the rule.
- Include concrete examples. Show what good output looks like, or contrast with what went wrong.
- Procedural skills need fallbacks. If the skill prescribes steps, explicitly state what to do if each step fails.
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 · 94 lines · 132 tokens per session scan A 776657164dbb
improve-urself is a skill published in the GitHub repository Stealthy-McStealth/self-evolve (5 stars, last pushed 3mo ago), licensed MIT. It adds 132 tokens to every session and 805 once invoked, about $0.0007 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
compare-screenshots
Compare screenshots to judge which image is less wrong, not to match a baseline. Use when a UI, game, document, render, chart, or generated asset needs objective visual telemetry, side-by-side inspection, crop/zoom review, or a fresh second opinion before accepting or rejecting a visual change.
release
Increment the package version, commit the release, create a matching version tag, and push main plus the tag. Use when releasing this repo, publishing the package, bumping the version, tagging a release, or when the user asks to "release", "bump ver", "tag", or "push tags".
refactor-clean
Refactor cleanly instead of layering sediment. Use when a change reveals duplicated concepts, local adapters, obsolete owners, compatibility wrappers, parallel abstractions, an over-large module that has accreted many responsibilities, or "just tack this on" pressure in any code area.
screenshot-critique
Use the unprimed sub agent as a second set of eyes before accepting visual work — MANDATORY before declaring any user-reported visual bug fixed or claiming a visual change verified; primed eyes pass defects fresh eyes catch.
code-review
Review changed code for naming, stale references, unnecessary complexity, and comment quality. Use after completing implementation work, before committing, or when the user asks to review or audit code.
write-skills
Create or revise agent skills. Use when adding a new skill file, renaming a skill, simplifying an existing skill, improving trigger descriptions, or deciding what belongs in a skill versus references, scripts, assets, or ordinary docs.