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 ratnesh-maurya/cursor-claude-personas --skill evolutiongit clone --depth 1 https://github.com/ratnesh-maurya/cursor-claude-personasWrote 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/ratnesh-maurya/cursor-claude-personas/evolution)<a href="https://agentmods.dev/skills/ratnesh-maurya/cursor-claude-personas/evolution"><img src="https://agentmods.dev/badge/skills/ratnesh-maurya/cursor-claude-personas/evolution/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/ratnesh-maurya/cursor-claude-personas/evolution"><img src="https://agentmods.dev/badge/skills/ratnesh-maurya/cursor-claude-personas/evolution.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 | $0.00061 | $0.02734 |
| Opus 5 | $0.00030 | $0.01367 |
| Sonnet 5 | $0.00012 | $0.00547 |
| Haiku 4.5 | $0.00006 | $0.00273 |
Grade C, and why
evolution scanned grade C with 2 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 9d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/ZhangHanDong/makepad-skills/main/install.sh | bash -s -- --with-hooks Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
<!-- security-allowlist: curl-pipe-bash --> How it starts
The opening of the file, as written. The whole thing — 421 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Makepad Skills Evolution
This skill enables makepad-skills to self-improve continuously during development.
Quick Navigation
| Topic | Description |
|---|---|
| Collaboration Guidelines | Contributing to makepad-skills |
| Hooks Setup | Auto-trigger evolution with hooks |
| When to Evolve | Triggers and classification |
| Evolution Process | Step-by-step guide |
| Self-Correction | Auto-fix skill errors |
| Self-Validation | Verify skill accuracy |
| Version Adaptation | Multi-branch support |
Hooks-Based Auto-Triggering
For reliable automatic triggering, use Claude Code hooks. Install with --with-hooks:
# Install makepad-skills with hooks enabled
curl -fsSL https://raw.githubusercontent.com/ZhangHanDong/makepad-skills/main/install.sh | bash -s -- --with-hooks
This will install hooks to .claude/hooks/ and configure .claude/settings.json:
{
"hooks": {
"UserPromptSubmit": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "bash .claude/hooks/makepad-skill-router.sh"
}
]
}
],
"PreToolUse": [
{
"matcher": "Bash|Write|Edit",
"hooks": [
{
"type": "command",
"command": "bash .claude/hooks/pre-tool.sh"
}
]
}
],
"PostToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "bash .claude/hooks/post-bash.sh"
}
]
}
]
}
}
What Hooks Do
| Hook | Trigger Event | Action |
|---|---|---|
makepad-skill-router.sh |
UserPromptSubmit | Auto-route to relevant skills |
pre-tool.sh |
Before Bash/Write/Edit | Detect Makepad version from Cargo.toml |
post-bash.sh |
After Bash command fails | Detect Makepad errors, suggest fixes |
session-end.sh |
Session ends | Prompt to capture learnings |
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.
- 9d ago First seen · 421 lines · 61 tokens per session scan C df45f8367f93
evolution is a skill published in the GitHub repository ratnesh-maurya/cursor-claude-personas (8 stars, last pushed 5mo ago), licensed MIT. It adds 61 tokens to every session and 2,734 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
requirements-authoring
To author, update, and validate functional/non-functional requirements as atomic units with user approval.
ijfw-plan
Use when the user says 'plan this', 'plan it', 'make a plan', 'let's plan', 'draft a plan', 'how should we tackle this', 'break this down', or invokes '/ijfw-plan'. Produces a falsifiable PLAN.md (software, book, campaign, design, research) with task breakdown, dependency wave-table, and success criteria — gated by…
hitl
Rosetta CRITICAL MUST skill to load as Prep Step 3 Step 2 — immediately after orchestrator-contract, right before loading any workflow. Loads the session-wide approval-gate protocol governing when to stop and wait vs proceed. WITHOUT IT decisions proceed silently, violating enterprise policy. Activate it for ALL tasks…
research
To run systematic deep research via meta-prompting — grounded references, incremental tracking, self-validation.
deviation
Rosetta CRITICAL MUST skill. MUST activate when intent is unclear, you cannot follow original intent, you cannot easily or reliably solve the problem, something came as SURPRISE or UNEXPECTED, you cannot bet $100 on your solution, you detect unknowns or assumptions that critically affect the solution, you detect…
skillnote
Self-hosted skill registry for OpenClaw. Stores procedures your team writes (name, description, body), syncs them to disk before each task, and collects which-helped/which-failed signals from the agent so the registry improves over time.