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 MauricioPerera/llms-txt-skills --skill api-clientgit clone --depth 1 https://github.com/MauricioPerera/llms-txt-skillsWrote 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/mauricioperera/llms-txt-skills/api-client)<a href="https://agentmods.dev/skills/mauricioperera/llms-txt-skills/api-client"><img src="https://agentmods.dev/badge/skills/mauricioperera/llms-txt-skills/api-client/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/mauricioperera/llms-txt-skills/api-client"><img src="https://agentmods.dev/badge/skills/mauricioperera/llms-txt-skills/api-client.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 | $0.00042 | $0.00569 |
| Opus 5 | $0.00021 | $0.00284 |
| Sonnet 5 | $0.00008 | $0.00114 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
api-client scanned grade A 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
import urllib.request What it actually says
api-client
Patterns for calling the img.automators.work HTTP API to generate SVG placeholder images.
When to use
- The user needs a placeholder image for a UI mockup.
- The user wants an SVG with specific dimensions (
{width}x{height}). - The user wants a colored background (
?bg={hex6}). - The user is building HTML or CSS that references a placeholder image.
Do NOT use this skill for:
- Production images, photography, or real content.
- Images larger than 4000px in any dimension.
- When the user is already using a design system with built-in skeleton components.
Base URL
https://img.automators.work
Endpoint
GET /{width}x{height}[?bg={hex6}]
width,height: integers in px, each <= 4000.bg(optional): 6-digit hex without#. Defaults tocccccc.
Python request pattern
import urllib.request
url = "https://img.automators.work/400x300?bg=1e3a5f"
req = urllib.request.Request(url, headers={"Accept": "image/svg+xml"})
with urllib.request.urlopen(req, timeout=15) as resp:
svg = resp.read().decode("utf-8")
Error handling
import urllib.error
try:
with urllib.request.urlopen(req, timeout=15) as resp:
svg = resp.read().decode("utf-8")
except urllib.error.HTTPError as e:
if e.code == 400:
raise RuntimeError("Invalid dimensions: must be integers in format {width}x{height}")
raise RuntimeError(f"HTTP {e.code}: {e.reason}")
except urllib.error.URLError as e:
raise RuntimeError(f"Connection failed: {e.reason}")
Constraints
- Stateless, no auth, no rate limit beyond Cloudflare platform default.
- Responses are immutable and cached one year.
- Only endpoint is
/{W}x{H}. Do not invent paths.
Failure modes
- HTTP 400:
widthorheightis not an integer, or path does not match{int}x{int}. - Invalid
bg: SVG still returns but with default gray background (cccccc).
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 First seen · 77 lines · 42 tokens per session scan A 2a2493a78e2f
api-client is a skill published in the GitHub repository MauricioPerera/llms-txt-skills (2 stars, last pushed 12d ago), licensed MIT. It adds 42 tokens to every session and 569 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (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
design-it-twice
Generates and compares at least two fundamentally different design alternatives on concrete criteria before committing. Use when the user asks to design something twice, or before committing to any significant design of classes, modules, APIs, or architecture. Not for judging strategic vs. tactical investment in…
design-review
Orchestrates a structured design review, running the other skills as a diagnostic funnel from complexity triage to a full red-flags sweep. Use when reviewing a file, module, or PR for overall design quality and you want a comprehensive, prioritized assessment. Not for applying one specific lens (use that skill…
API Design Checklist
Naming, status-code, error-shape, and versioning conventions for keeping an API internally consistent as it grows.
api-designer
Generates complete, production-ready REST API endpoint specifications for any system or domain the user describes.
api-integration
Designs event-driven architectures, webhook systems, API chaining flows, ETL pipelines, and integration patterns between services.
api-design-principles
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers and stand the test of time.