Borrowing it
Nothing to install: this file belongs to albertomarturelo/sii. 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/albertomarturelo/sii/main/.agents/skills/run-sii/SKILL.mdgit clone --depth 1 https://github.com/albertomarturelo/siiWrote 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/albertomarturelo/sii/run-sii)<a href="https://agentmods.dev/skills/albertomarturelo/sii/run-sii"><img src="https://agentmods.dev/badge/skills/albertomarturelo/sii/run-sii/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/albertomarturelo/sii/run-sii"><img src="https://agentmods.dev/badge/skills/albertomarturelo/sii/run-sii.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00081 | $0.01203 |
| Opus 5.5 | $0.00032 | $0.00481 |
| Sonnet 5.5 | $0.00016 | $0.00241 |
| Haiku 4.5 | $0.00008 | $0.00120 |
Grade A, and why
run-sii 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 yesterday.
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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sii is a CLI (packages/cli), an MCP stdio server (packages/mcp) and the core they share
(packages/core). The agent path is driver.mjs in this skill. It runs the BUILT binaries
with SII_HOME set to a scratch dir, speaks JSON-RPC to the MCP server, and calls core tasks
against the core's own fakes (testing). Paths below are relative to the repo root;
.claude/skills is a symlink to .agents/skills, so either path works.
Build
pnpm install --frozen-lockfile
pnpm build
The driver reads packages/*/dist. Rebuild after every source change, or it runs stale code.
Run (agent path)
One command checks everything: CLI, MCP handshake + a tool + a resource, a core task vs fakes.
node .claude/skills/run-sii/driver.mjs smoke
It prints PASS/FAIL per check and exits non-zero on any failure. Pieces:
D=.claude/skills/run-sii/driver.mjs
node $D home --reset --seed # fresh scratch SII_HOME + a synthetic session (11111111-1)
node $D cli auth status # any sii args; JSON on stdout, exit code preserved
node $D cli --human operate --list
node $D cli f29 submit --help # --help of any verb is offline
node $D mcp tools # tool names (32 today)
node $D mcp resources # sii://session, sii://operating, sii://operable, sii://config
node $D mcp read sii://operating
node $D mcp call auth_status
node $D mcp call operate '{"list":true}'
node $D core whoami # a domain task vs FakePortalDriver: result + audit entries
Direct invocation is the path most PRs need. Most PRs touch a portal facade or a task,
and those only run against fakes. core whoami in driver.mjs is the template: build a
Runtime from testing.FakePortalDriver / FixedClock / RecordingAuditSink /
InMemoryKeyValueStore, call testing.seedSession, call the task. Script the fake with
requestJson / requestText / requestBinary for the surface you changed. Copy a fixture
from that module's *.test.ts.
What ships with it
1 file 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.
- yesterday First seen · 97 lines · 81 tokens per session scan A cc45247bb30b
run-sii is a skill published in the GitHub repository albertomarturelo/sii (16 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 1,203 once invoked, about $0.0003 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 2026-10-24.
Other skills, from other repositories
implement
Fill in the stub modules of a pipeline emitted by rote, so it actually runs. Use after rote emit or rote compile when the emitted app still has extracted/ stubs that raise a "[rote stub]" error or a bare NotImplementedError, or when the user says "implement the stubs", "fill in the extracted modules", "make the…
journey-simulation
Use when caller wants to observe how a stranger encounters a flow, artifact, or sandbox — triggers like "simulate a user journey", "test our onboarding / checkout / signup", "will my ICP convert", "how does a cold reader experience this README", "first-time user test", "cognitive walkthrough", or any request to…
pursr
Use Pursr for browser screenshots, scripted visual operation, visual regression, accessibility audits, DOM inspection, and MCP-driven browser sessions. Use when a user asks an agent to inspect a site, operate an existing browser session, fill or draft UI content, record a tutorial, compare visuals, debug layout, or…
accessibility-checks
Use when verifying accessibility (WCAG 2.2 AA) of a rendered UI in a real browser before reporting done — the omp-native replacement for the chrome-devtools a11y plugin. Runs a concrete ordered checklist with omp's builtin browser tool (open tab → tab.evaluate DOM query / elementFromPoint / getComputedStyle /…
ui-verify-checks
Use when verifying a frontend UI change in a real browser before reporting done. The canonical 7-check list (real auth → render≠behavior → scroll containment → primary-button reachability → selection-state sync → responsive → console) + environment fail-fast rule (transport-unreachable vs HTTP error distinction) +…
chrome-verify-checks
Use when verifying a chrome-extension/ change before reporting done. The canonical 7-check list (build → Service Worker vm.createContext compat → manifest sanity → per-site content-script DOM contract → message-passing trace → test suite → manual-load checklist) + verdict rules. chrome-extension/ is a strong-guard…