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.
git clone --depth 1 https://github.com/textura-agency/next16-claude-starterWrote 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/commands/textura-agency/next16-claude-starter/load)<a href="https://agentmods.dev/commands/textura-agency/next16-claude-starter/load"><img src="https://agentmods.dev/badge/commands/textura-agency/next16-claude-starter/load/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/commands/textura-agency/next16-claude-starter/load"><img src="https://agentmods.dev/badge/commands/textura-agency/next16-claude-starter/load.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 | $0.00021 | $0.00566 |
| Opus 5.5 | $0.00008 | $0.00226 |
| Sonnet 5.5 | $0.00004 | $0.00113 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
load 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 11d 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.
What it actually says
Audit and fix load for: $ARGUMENTS (the home route if empty).
Use the optimize-load skill. The loop is the point:
yarn build && yarn start— never auditnext dev.yarn qa:setuponce.- Baseline first:
node tools/qa/lighthouse.mjs --url http://localhost:3000/ --runs 3and again with--as-bot— all four categories × mobile/desktop × people and robot (crawlers and PageSpeed get the robot form).--ab <reference>interleaves an A/B on a busy machine. Medians; 5 runs before calling a regression. Thennode tools/qa/axe-sweep.mjs --url …— contrast through the whole entrance, and at-rest failures Lighthouse can't see over a canvas. - Attribute before fixing. Read the LCP phase breakdown and the LCP
element's timing; the
PerformanceObserverprobe for CLS; name TBT's code withnode tools/qa/profile.mjs --url …(Lighthouse's long-task times are simulated). Checkobsidian/knowledge/fix-catalog.mdfirst. - Fix one thing, re-measure with the identical config.
.claude/scripts/verify.sh,yarn lint,yarn build, andqa-verifyif any UI changed — a contrast fix changes how the page looks.
The bar: Performance ≥ 90 on mobile and desktop; Accessibility, Best
Practices and SEO = 100, people and robot. A mid-fade A11y flake is fixable
without changing the look (reveal by transform/clip/mask with opacity 1). Local
numbers are a floor — take the record on the deployed URL (--url https://…).
For scroll jank after load use optimize-performance; for a three.js/WebGL scene
run optimize-3d-scene first; for real-phone behaviour mobile-device-qa.
Report the full grid before and after, what you changed, what you reverted, and
what you did not fix and why — especially anything capped by a design decision
rather than a bug (with its measured cost). Close with the retro: measured fixes
→ obsidian/knowledge/fix-catalog.md, traps → obsidian/knowledge/pitfalls.md.
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.
- 11d ago Changed · +8 lines · +5 tokens per session 3098876b3f35
- 29d ago First seen · 29 lines · 16 tokens per session scan A 912cf1bf494f
load is a command published in the GitHub repository textura-agency/next16-claude-starter (137 stars, last pushed 3d ago), licensed Unlicense. It adds 21 tokens to every session and 566 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-19.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.