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 skills/henryqin1997/statem/use-statemnpx skills add henryqin1997/statem --skill use-statemgit clone --depth 1 https://github.com/henryqin1997/statemWrote 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/henryqin1997/statem/use-statem)<a href="https://agentmods.dev/skills/henryqin1997/statem/use-statem"><img src="https://agentmods.dev/badge/skills/henryqin1997/statem/use-statem.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 | $0.00040 | $0.01040 |
| Opus 5 | $0.00020 | $0.00520 |
| Sonnet 5 | $0.00008 | $0.00208 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
use-statem 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 5d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use Statem
Use statem as a state-aware runbook for long agent runs. It should guide the work and preserve progress without turning the session into a rigid workflow harness.
Operating Loop
- Inspect or create a spec such as
statem.yaml. - Run
statem validate statem.yaml --json. - Start or resume with
statem start statem.yaml --run-id <id> --json. - Before work, run
statem cur --run-id <id> --json. - When a state is complete, run
statem goto <next> --run-id <id> --json. - Before pausing, run
statem save --run-id <id> --json. - For handoff context, read recent history:
statem history --run-id <id> --tail 10 --json.
If statem is not on PATH, use python3 -m statem from the repository that contains the Python package.
For dynamic servers, company machines, or disposable git checkouts, prefer a
machine-local state directory. Set STATEM_STATE_DIR once, for example
$HOME/.local/state/statem/<project>, so runtime state survives checkout
replacement. After moving to a new checkout, run statem start <spec> --run-id <id> once to rebind the run to the current spec path.
Commit YAML runbooks with the repo. Do not commit runtime state; treat .statem/
or STATEM_STATE_DIR as local, copy-on-use execution data.
Context Clear
Avoid /clear in normal loops. It flushes the conversation, including any
instructions that were supposed to run after it, and can lose useful intent that
was not written to durable files. Prefer explicit transitions plus safe
compaction. Before a hard clear, run
statem prompt --run-id <id> and paste the generated prompt immediately after
/clear. After a hard clear, recover from .statem with start, cur, and
history instead of relying on previous chat context.
Loop Compaction
For cyclic runbooks, prefer an explicit session hygiene node after a full loop.
When another cycle will continue and the context is noisy, run
statem compact-prompt --run-id <id>, use the generated /compact
instruction, then recover with statem cur and statem history --tail 10.
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.
- 5d ago First seen · 89 lines · 40 tokens per session scan A 10ffb971262a
use-statem is a skill published in the GitHub repository henryqin1997/statem (969 stars, last pushed 3d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,040 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…