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/onewave-ai/open-agent-stack/add-featurenpx skills add OneWave-AI/open-agent-stack --skill add-featuregit clone --depth 1 https://github.com/OneWave-AI/open-agent-stackWrote 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/onewave-ai/open-agent-stack/add-feature)<a href="https://agentmods.dev/skills/onewave-ai/open-agent-stack/add-feature"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/add-feature.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 | $0.00059 | $0.00577 |
| Opus 5 | $0.00030 | $0.00289 |
| Sonnet 5 | $0.00012 | $0.00115 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
add-feature 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 3d 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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Feature
Feature five is where vibe-coded apps fall apart. Not because the feature is hard, but because it gets built as if the first four did not exist: a second button component, a second way to fetch, a second set of colors. Entropy, not complexity, is what makes these apps unmaintainable.
Workflow
- Read before you write. Find the closest existing thing to what is being added and read it fully -- a similar route, a similar form, a similar data fetch. The answer to "how should I build this" is usually already in the repo. Note the conventions actually in use, not the ones the README claims.
- Name the blast radius. List what this feature touches: routes, shared components, types, the data layer, anything that reads the same state. If it touches something on the money path (signup, checkout, the core action), say so out loud before starting.
- Extend, do not duplicate. Reuse the existing primitives and add variants to them. A second
Button.tsx, a second fetch helper, or a second color scale is a bug being introduced on purpose. If the existing primitive genuinely cannot flex, refactor it once and migrate the old callers -- do not fork it. - Build the whole feature. Real data path, loading state, empty state, error state, mobile layout. A feature that only handles the happy path is not shipped, it is demoed.
- Verify what you broke. Run the app and walk the new flow AND the flow nearest to it. Run the build (
npm run build, not just dev). Typecheck clean. If tests exist, they pass; if they do not exist, say so rather than implying coverage.
Rules
- Match the surrounding code's idiom -- naming, file layout, comment density -- even where you would have chosen differently. Consistency beats your preference.
- No new dependency without saying why the existing stack cannot do it. Every package is a future upgrade problem.
- Touch the design tokens, not the components' hardcoded values; a feature that introduces raw hex undoes the theme.
- If the feature reveals that an earlier shortcut has to go (mock data, a stubbed auth check), fix it now or write it down in the summary -- never build on top of it silently.
- Summarize as: what was added, what was changed that already existed, what to click to verify.
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.
- 3d ago First seen · 25 lines · 59 tokens per session scan A 575cbc3bd9a3
add-feature is a skill published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 23d ago), licensed MIT. It adds 59 tokens to every session and 577 once invoked, about $0.0003 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
html-email
Send-ready single-file email.
a11y-review
Static analysis pass over JSX/HTML/CSS source for WCAG 2.2 AA failure patterns. Does NOT run axe-core, does NOT measure real contrast, does NOT test runtime behavior — pair with a11y-testing for that. Use when the user asks for an accessibility review, a11y check, WCAG review, "is this accessible?", "does my site meet…
colors
Color systems for web interfaces — OKLCH conversion and palette generation, contrast measurement (APCA/WCAG), gamut and P3 fallbacks, theming, one meaning per color. INVOKE PROACTIVELY when converting color values, building or extending a palette or token set, checking or reporting contrast, or theming light and dark…
a11y-keyboard-focus
Use this skill when the user asks about keyboard navigation, keyboard accessibility, focus management, focus trapping, focus ring, focus indicator, ":focus-visible", skip links, "tabindex", "Tab key navigation", "focus order", "focus returns", "orphaned focus", "focus lost", "modal focus trap", "focus after close"…
a11y-semantic-html
Use this skill when the user asks about semantic HTML structure, heading hierarchy, landmark regions, div soup, divitis, "which HTML element should I use", "semantic markup", "HTML accessibility", "ARIA landmarks", "page structure", "section vs div", "article vs section", "when to use aside", or is writing HTML…
typography
Web typography — typeface choice and pairing, variable fonts and OpenType features, type scales, line-height, letter-spacing, measure, wrapping, truncation, underlines, tabular numbers, iOS input zoom. INVOKE PROACTIVELY when styling or reviewing anything that renders text. The words themselves: [[ux-writing]]…