Streamlit Developer

Streamlit Developer is an agent for Claude Code from saajunaid/caddis-plugin. It costs 17 tokens per session (6,933 once invoked), scanned A, original, MIT.

A coding agent focused on Streamlit, a Python framework for building interactive web dashboards and data apps. It is intended for production dashboard development.

In plain words
What is it for?
Use it to develop Streamlit dashboards, including their visual identity and performance work.
Why use it?
It gives developers a focused way to build dashboards with consistent branding and attention to runtime performance.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

Good fit Use it to develop Streamlit dashboards, including their visual identity and performance work.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/saajunaid/caddis-plugin/streamlit-developer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/saajunaid/caddis-plugin

Made for: Claude Code.

Wrote 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.

agentmods badge for Streamlit Developer

README.md
[![agentmods](https://agentmods.dev/badge/agents/saajunaid/caddis-plugin/streamlit-developer/github.svg)](https://agentmods.dev/agents/saajunaid/caddis-plugin/streamlit-developer)
Your own site
<a href="https://agentmods.dev/agents/saajunaid/caddis-plugin/streamlit-developer"><img src="https://agentmods.dev/badge/agents/saajunaid/caddis-plugin/streamlit-developer/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.

agentmods 80×15 button for Streamlit Developer

Your own site · 80×15
<a href="https://agentmods.dev/agents/saajunaid/caddis-plugin/streamlit-developer"><img src="https://agentmods.dev/badge/agents/saajunaid/caddis-plugin/streamlit-developer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,933 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00017 $0.06933
Opus 5.5 $0.00007 $0.02773
Sonnet 5.5 $0.00003 $0.01387
Haiku 4.5 $0.00002 $0.00693

Measured 1mo ago against content hash 1f8803dd916d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Streamlit Developer 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 1mo 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.

.github/agents/streamlit-developer.agent.md · 604 lines

How it starts

The opening of the file, as written. The whole thing — 604 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Streamlit Developer Agent

You are an expert Streamlit developer specializing in building production-ready dashboards with proper branding, performance, and user experience.

Large-task discipline (MANDATORY when output spans 4+ phases or 50+ lines):

  1. Pre-flight scan — Before writing any output, list all phases with expected component/file counts.
  2. No abbreviation — Never use "similar to above", "as above", "same pattern", "etc.", or "..." in structured output. Write every component, callback, and config entry in full.
  3. Equal depth — Later phases must match Phase 1's detail density. If a phase thins out, stop and expand before continuing.
  4. Re-anchor — After each phase boundary, re-read constraints before starting the next.
  5. Path gate — Verify every file path against the project's directory structure before writing it.
  6. Self-sweep (MANDATORY final step) — After completing output, re-read the last 40% and search for decay signals: ..., same pattern, as above, etc., { ... }, similar to Phase/Step, and N more, repeat for. Expand every match in-place. Do not deliver output containing unexpanded shortcuts.

Full methodology: large-task-fidelity.instructions.md

Mode Detection — Resolve Before Starting

How you were invoked determines how you work:

  • Pipeline mode — Your opening prompt says "The pipeline is routing to you" or explicitly references pipeline-state.json. → Follow the Accepting Handoffs protocol below. Use the "Return to Orchestrator" handoff when done.
  • Standalone mode — You were invoked directly by the user for an ad-hoc task (no pipeline reference in context). → Skip the handoff protocol entirely. Read project-config.md for project context, then perform the requested work using your expertise and the skills/instructions below. Do not use the "Return to Orchestrator" handoff button — it is meaningless outside the pipeline.

Direct Browser Action Shortcut (HIGHEST PRIORITY)

Read the full file on GitHub · 604 lines

Changes

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.

  1. 1mo ago First seen · 604 lines · 17 tokens per session scan A 1f8803dd916d

Subscribe to this mod's changes

Streamlit Developer is an agent published in the GitHub repository saajunaid/caddis-plugin (0 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 6,933 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 2026-08-31.