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 OutlineDriven/outline-driven-development --skill first-load-byte-reductiongit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/first-load-byte-reduction)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/first-load-byte-reduction"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/first-load-byte-reduction/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/outlinedriven/outline-driven-development/first-load-byte-reduction"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/first-load-byte-reduction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.00806 |
| Opus 5 | $0.00026 | $0.00403 |
| Sonnet 5 | $0.00010 | $0.00161 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
first-load-byte-reduction 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 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.
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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
First-load byte reduction
Contract
| Field | Bound contract |
|---|---|
| Trigger | A first screen needs lower transfer bytes without visual or behavioral change. |
| Authority | Reversible local with dependency ask: write only named local artifacts; ask before adding or upgrading a dependency. |
| Side effect | Pixel-identical first-load byte reduction: local writes to the fixed screens and their asset pipeline. |
| Done | The fixed first screen transfers fewer compressed bytes with pixel identity and passing tests. |
| Stop | No safe reduction; blocked; budget exhausted. Bound: fixed screens, target environment, byte budget. |
Inputs
- Fixed screens (required): the exact pages or routes to reduce, named before any mutation.
- Target environment (required): the browser, device, or network condition that defines the measurement context.
- Byte budget (required): the target compressed byte count or percentage reduction, declared before work begins.
Procedure
- Bind the fixed screens, target environment, and byte budget. Freeze all three before any mutation. Done when: the screens, environment, and budget are named and frozen.
- Capture the baseline. For each fixed screen, measure the compressed transfer bytes in the target environment using a network waterfall or build-output size report. Record the per-resource byte breakdown: HTML, CSS, JavaScript, images, fonts, other. Simultaneously capture the visual identity rubric: a full-page screenshot at the target viewport and the rendered DOM structure. Done when: baseline bytes and visual identity are recorded.
- Execute byte reduction inside the bound. Apply asset and bundle optimizations that preserve visual and behavioral identity: compress and resize images to the display dimensions, subset fonts to the used glyphs, tree-shake unused JavaScript, split bundles by route, inline critical CSS, defer non-critical resources, compress text assets with Brotli or gzip. Ask before adding or upgrading a dependency. Done when: the reduced screen transfers fewer compressed bytes than the baseline.
- Prove pixel identity. Render the reduced screen at the same viewport as the baseline. Compare the full-page screenshot pixel-by-pixel against the baseline screenshot. Tolerances: zero pixel difference for static content; animated or lazy-loaded content must reach the same final rendered state. Run the test suite to confirm no behavioral regression. Done when: pixel identity is confirmed and tests pass.
- Stop at success (fewer bytes with pixel identity and passing tests), any non-success terminal, or the bound. Done when: a terminal class is reached and named.
- Persist the run record to
.outline/loops/first-load-byte-reduction/<run_id>/when durable. Emitreceipt.jsonbefore return. Done when: the receipt is written with before/after byte counts, pixel-identity confirmation, and test result.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 43 lines · 51 tokens per session scan A 6f96327f9172
first-load-byte-reduction is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 4d ago), licensed Apache-2.0. It adds 51 tokens to every session and 806 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 2026-09-03.
Other skills, from other repositories
typography-audit
Use when asked to audit typography across a codebase. Produces a file:line report with concrete fixes ordered by impact and flags unverifiable rules. Not for building a type system or token scale.
polished-web-prototype
Use when /polished-web-prototype runs or a user builds an artifact from a mockup, design plan, or brief. Not for variant galleries: use design-variants. Not for live audits: use web-design-review.
ui-design
Use when directing, building, or auditing React/Next.js Tailwind UI: visual direction, responsive/dark-mode retrofits, UX audits. Not for typography or motion: use typography-audit or ui-animation.
web-design-review
Use when the user runs /web-design-review with a URL to visually audit and fix a live UI. Not for design direction: use design. Not for variant galleries: use design-variants.
frontend-ui-engineering
Use when asked to build or modify production-quality components, layouts, state, and pages with WCAG 2.1 AA and real content. Not for token-system design: use frontend-design-deslop.
frontend-design-deslop
Use when a user builds or styles a web frontend or asks to make it not look AI-generated. Not for component-level UI work without the token system: use frontend-ui-engineering.