Borrowing it
Nothing to install: this file belongs to iusztinpaul/designing-real-world-ai-agents-workshop. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/iusztinpaul/designing-real-world-ai-agents-workshop/main/.agents/skills/developing-with-streamlit/skills/using-streamlit-session-state/SKILL.mdgit clone --depth 1 https://github.com/iusztinpaul/designing-real-world-ai-agents-workshopWrote 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/iusztinpaul/designing-real-world-ai-agents-workshop/using-streamlit-session-state)<a href="https://agentmods.dev/skills/iusztinpaul/designing-real-world-ai-agents-workshop/using-streamlit-session-state"><img src="https://agentmods.dev/badge/skills/iusztinpaul/designing-real-world-ai-agents-workshop/using-streamlit-session-state/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/iusztinpaul/designing-real-world-ai-agents-workshop/using-streamlit-session-state"><img src="https://agentmods.dev/badge/skills/iusztinpaul/designing-real-world-ai-agents-workshop/using-streamlit-session-state.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 | $0.00050 | $0.00923 |
| Opus 5 | $0.00025 | $0.00462 |
| Sonnet 5 | $0.00010 | $0.00185 |
| Haiku 4.5 | $0.00005 | $0.00092 |
Grade A, and why
using-streamlit-session-state 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 12d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Streamlit session state
Streamlit reruns scripts top-to-bottom on every interaction. Without session state, variables reset each time. Use st.session_state to persist values across reruns.
Basic usage
Session state is a dictionary-like object supporting attribute and bracket notation:
# Initialize with setdefault (preferred)
st.session_state.setdefault("count", 0)
# Alternative: check before setting
if "count" not in st.session_state:
st.session_state.count = 0
# Read
current = st.session_state.count
# Update
st.session_state.count += 1
st.session_state["count"] = 5 # Bracket notation also works
# Delete
del st.session_state.count
Accessing uninitialized keys raises KeyError. Use st.session_state.get("key", default) for safe access.
Widget-state association
Every widget with a key parameter automatically syncs to session state:
name = st.text_input("Name", key="user_name")
# st.session_state.user_name contains the same value as `name`
Callbacks
Callbacks execute before the script reruns, allowing immediate state changes. Use on_change or on_click with optional args and kwargs:
def increment(amount):
st.session_state.count += amount
st.button("Add 5", on_click=increment, args=(5,))
Access a widget's value in its own callback via st.session_state.key, not the return variable.
Initialization patterns
Initialize all state at the top of your app for clarity:
st.session_state.setdefault("user", None)
st.session_state.setdefault("page", "home")
st.session_state.setdefault("filters", {})
Multipage state
Widgets are NOT stateful across pages. Their values reset when navigating between pages.
Sharing state
Use session state variables (not widget keys) to share data:
# Page 1: Store value
st.session_state.selected_user = st.selectbox("User", users)
# Page 2: Read stored value
if "selected_user" in st.session_state:
st.write(f"Selected: {st.session_state.selected_user}")
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.
- 12d ago First seen · 145 lines · 50 tokens per session scan A 1997bf4c7459
using-streamlit-session-state is a skill published in the GitHub repository iusztinpaul/designing-real-world-ai-agents-workshop (505 stars, last pushed 3mo ago), licensed MIT. It adds 50 tokens to every session and 923 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 2026-08-30.
Other skills, from other repositories
huggingface-gradio
Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots.
adk-agent-builder
Builds ADK (Agent Development Kit) Python agents: LLM agents with tools, graph workflows of function and agent nodes, conditional routing, fan-out and join, schema-validated delegation between agents, human-in-the-loop pauses, and pytest coverage for all of it. Use when asked to create an agent or a workflow, add a…
adk-style
Python style and codebase conventions for ADK (Agent Development Kit): private-by-default file visibility, imports, type hints, Pydantic v2 models, formatting, docstrings, logging, async I/O, file and test layout, and unit test structure. Use when writing or editing ADK source or tests, deciding whether a new file or…
hypothesis-testing
Property-based testing with Hypothesis for discovering edge cases and validating invariants. Use when implementing comprehensive test coverage, testing complex logic with many inputs, or validating mathematical properties and invariants across input domains. Triggered by: hypothesis, property-based testing, @given…
adk-verify-snippets
Checks that every Python code block in a Markdown file actually compiles and runs, by extracting each block to a temporary file, executing it in an isolated subprocess, and writing a pass/fail report with per-snippet coverage. Use when the user asks to verify, test, or validate the code samples in a README, a guide…
adk-setup
Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test run. Runs only when explicitly requested, never on its own. Use when asked to set up, bootstrap, or repair a development…