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/datahaskell/sabela/sizanpx skills add DataHaskell/sabela --skill sizagit clone --depth 1 https://github.com/DataHaskell/sabelaWrote 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/datahaskell/sabela/siza)<a href="https://agentmods.dev/skills/datahaskell/sabela/siza"><img src="https://agentmods.dev/badge/skills/datahaskell/sabela/siza.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 | $0.00061 | $0.06425 |
| Opus 5 | $0.00030 | $0.03213 |
| Sonnet 5 | $0.00012 | $0.01285 |
| Haiku 4.5 | $0.00006 | $0.00643 |
Grade A, and why
siza scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
**Every notebook operation goes through `${CLAUDE_PLUGIN_ROOT}/skills/siza/scripts/siza`.** Do not `curl` `/api/cell/*`, `/api/load`, `/api/notebook`, or any non-`/api/ai/*` endpoint, and do not `ps aux` looking for the How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
siza — Sabela notebook pair programming
The user has a Sabela notebook open in their browser. You are pairing with them: every change you make appears live in their UI. The notebook state is shared, including a long-lived GHCi session.
Hard rule
Every notebook operation goes through ${CLAUDE_PLUGIN_ROOT}/skills/siza/scripts/siza. Do not curl /api/cell/*, /api/load, /api/notebook, or any non-/api/ai/* endpoint, and do not ps aux looking for the server. Raw endpoints bypass the AI bridge: they skip the browser-refresh broadcast, skip optimistic-concurrency checks on cell hashes, and skip large-output handle stashing. If siza doesn't expose what you need, tell the user — don't reach around it. One sanctioned exception: setting widget state (slider/dropdown/lasso) via POST /api/widget, since siza has no widget-set tool — see reference/widgets.md. It still needs user sign-off before you curl it.
Never edit the notebook's .md file directly with file tools (Write/Edit/sed). The live session the user is looking at is the source of truth; editing the file on disk diverges from it, skips validation (the cell never runs), and skips the browser broadcast. Make every cell change through siza (insert_cell/replace_cell_source/delete_cell) so it is applied, auto-run, and visible. Saving the session back to disk is the user's action in the browser, not a file you write.
Discovery and invoking
The primary entrypoint is ${CLAUDE_PLUGIN_ROOT}/skills/siza/scripts/siza — a thin shim over the compiled typed client (exe:siza). It validates tool names and JSON against the typed contract, runs the pre-flight parse + security scan on mutating code, and records each call to a provenance log (see Provenance).
${CLAUDE_PLUGIN_ROOT}/skills/siza/scripts/siza discover # JSON array of live servers; the first is the target
${CLAUDE_PLUGIN_ROOT}/skills/siza/scripts/siza health # probe the first live server's health
${CLAUDE_PLUGIN_ROOT}/skills/siza/scripts/siza tool <name> '<json_input>'
${CLAUDE_PLUGIN_ROOT}/skills/siza/scripts/siza check [--strict] [-|FILE] # pre-flight parse + security scan of cell source
${CLAUDE_PLUGIN_ROOT}/skills/siza/scripts/siza annotate <cell_id> [--source] # infer signatures for a cell's unsigned binds
${CLAUDE_PLUGIN_ROOT}/skills/siza/scripts/siza await-idle [SECONDS] # block until the kernel settles to idle (re-loops past timedOut)
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 174 lines · 61 tokens per session scan A acd43873a4e1
siza is a skill published in the GitHub repository DataHaskell/sabela (114 stars, last pushed 11d ago), licensed MIT. It adds 61 tokens to every session and 6,425 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…