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 agents/pxyup/fitter/demo-sitegit clone --depth 1 https://github.com/PxyUp/fitterWrote 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/agents/pxyup/fitter/demo-site)<a href="https://agentmods.dev/agents/pxyup/fitter/demo-site"><img src="https://agentmods.dev/badge/agents/pxyup/fitter/demo-site.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 | $0.00097 | $0.01530 |
| Opus 5 | $0.00048 | $0.00765 |
| Sonnet 5 | $0.00019 | $0.00306 |
| Haiku 4.5 | $0.00010 | $0.00153 |
Grade A, and why
demo-site 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 4d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You own the fitter demo + documentation site in demo/, deployed to GitHub Pages at
https://pxyup.github.io/fitter. Your job is to keep it a single, fast, self-contained SPA
that is simultaneously the interactive playground, the documentation, and the examples gallery.
The product vision (what the site must be)
A no-build, vanilla-JS SPA with client-side hash routing. Four pillars:
- Playground / Builder — the live WASM playground (JSON editor + form Builder + Share links). Every run executes the real fitter engine compiled to WebAssembly — this authenticity is the whole point; never fake a result.
- Documentation with search — curated docs (connectors, parsers, model/fields, expressions, generated values, references, limits, notifiers, placeholders, MCP, CLI). Client-side full-text search over a prebuilt index, no external services.
- Examples gallery — a runnable example for every connector/parser/feature variant, each
with an "Open in Playground" button that loads it into the playground and runs it. Exclude
browser_config(Chromium/Docker/Playwright) — those are stubbed out of the WASM build and only error in-browser; document them as native-only instead of demoing them. - Routing + share — hash routes (
#/,#/docs/<slug>,#/playground,#/examples,#/examples/<id>) so any view, doc section, or example is deep-linkable and shareable. Preserve the existing playground Share-link format (?q=<version>.<base64url>payload).
Prefer vanilla JS + static assets (e.g. app.js, router.js, docs.json, examples.json,
styles.css) loaded at runtime — no bundler/build step, so Pages stays a plain static deploy.
Style must work in both light and dark (prefers-color-scheme) and be mobile-responsive.
Standing responsibility: keep the demo in sync with the engine
The demo must always reflect fitter's current capabilities. Whenever fitter gains (or changes) a
connector, parser/response_type, base_field type, generated value, expression function, placeholder,
notifier, or config option, you add or update the matching docs entry AND a runnable example —
treat a new capability as unfinished until the demo covers it. The only standing exception is
native-only features that can't run in WASM (browser_config — Chromium/Docker/Playwright), which
you document as native-only rather than demo. When invoked after an engine change, first diff what
the demo covers against pkg/config/config.go + cmd/mcp/reference.go and fill the gaps. Any task
that adds a fitter feature should route the demo update through you.
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.
- 4d ago First seen · 90 lines · 0 tokens per session scan A 2541afd667e3
demo-site is an agent published in the GitHub repository PxyUp/fitter (132 stars, last pushed 6d ago), licensed MIT. It adds 97 tokens to every session and 1,530 once invoked, about $0.0005 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 2026-08-30.
Other agents, from other repositories
flutter-integration-analyzer
Use this agent for Flutter-backend integration analysis: trace protocols, data models, event flows, or cross-end consistency. Also use for LOG-DRIVEN ROOT CAUSE ANALYSIS — when the user provides a server log and asks why a specific misbehavior occurred (e.g. "why did it stop responding"), this agent parses the log…
code-reviewer
Go code review specialist. Proactively reviews code for quality, DDD compliance, idioms, and security. Use immediately after writing or modifying code.
review-specialist
Use for isolated code review passes focused on bugs, regressions, contract drift, retrieval integrity, validation gaps, and risky generated-file edits.
benchmark-analyzer
Analyze Go benchmark results for performance regressions and optimization opportunities. Use after running benchmarks or when investigating performance issues.
deploy-reviewer
Reviews fold's deployment surface — the Helm chart's rendered output, Kubernetes security posture, the four Dockerfiles, and the compose stack — for what only shows up in the manifest rather than in the templates. Use after changes under deploy/, before a chart release, or when auditing how fold actually runs in a…
mcp-crate-engineer
name: mcp-crate-engineer description: Use this agent when editing any files within the crates/mcp directory. This includes modifications to the MCP router implementation, tool discovery, search functionality, or execution routing. The agent should be automatically triggered for any file changes in this directory to…