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/dirien/yet-another-agent-harness/sync-websitenpx skills add dirien/yet-another-agent-harness --skill sync-websitegit clone --depth 1 https://github.com/dirien/yet-another-agent-harnessWrote 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/dirien/yet-another-agent-harness/sync-website)<a href="https://agentmods.dev/skills/dirien/yet-another-agent-harness/sync-website"><img src="https://agentmods.dev/badge/skills/dirien/yet-another-agent-harness/sync-website.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 | $0.00123 | $0.00786 |
| Opus 5 | $0.00062 | $0.00393 |
| Sonnet 5 | $0.00025 | $0.00157 |
| Haiku 4.5 | $0.00012 | $0.00079 |
Grade B, and why
sync-website scanned grade B with 1 finding 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 5d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
| Skills | `ls .claude/skills/` — count directories that contain a SKILL.md | How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sync Website
Keep website/index.html in sync with the yaah project's actual capabilities.
Why this matters
The website is a static single-page site in website/. It auto-deploys to GitHub Pages on push to main (via .github/workflows/deploy-pages.yaml). When features change in the Go code but the website isn't updated, users see stale information.
Data sources and website sections
Each website section has a canonical source of truth. Read the source first, then update the HTML.
| Website section | HTML landmark | Source of truth |
|---|---|---|
| Hero stats (4 numbers) | .hero-stats .stat-number |
Count from registries below |
| Features grid | #features .features-grid |
README.md features + pkg/ packages |
| How It Works | #how-it-works |
README.md quick-start |
| Multi-Agent table | #agents .table-wrapper |
pkg/generator/ — one file per agent |
| Install methods | #install .install-grid |
README.md install section |
| CLI Reference | #cli .cli-grid |
cmd/yaah/main.go + internal/cli/ cobra commands |
How to count for hero stats
| Stat | How to count |
|---|---|
| Agents | Number of generators in pkg/generator/ (claude, opencode, codex, copilot) |
| Skills | ls .claude/skills/ — count directories that contain a SKILL.md |
| Hooks | Count distinct handler types in pkg/hooks/handlers/ |
| Sub-Agents | ls .claude/agents/ — count .md files |
How to sync
-
Audit — Read the source of truth for the section that changed. Read
website/index.htmlto see what's currently shown. -
Diff — Identify what's new, removed, or changed.
-
Edit — Update
website/index.htmlwith the Edit tool. Match existing HTML patterns exactly:- Feature cards:
<div class="feature-card">with<h3>and<p> - CLI items:
<div class="cli-item">with<code>for command,<p>for description - Stats:
<div class="stat">with<span class="stat-number">and<span class="stat-label"> - Install cards:
<div class="install-card">with code blocks
- Feature cards:
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.
- 5d ago First seen · 58 lines · 123 tokens per session scan B 9959b92af0e2
sync-website is a skill published in the GitHub repository dirien/yet-another-agent-harness (20 stars, last pushed 3mo ago), licensed MIT. It adds 123 tokens to every session and 786 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…