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 skills add SII-Holos/synergy --skill change-computer-runtimegit clone --depth 1 https://github.com/SII-Holos/synergyWrote 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/sii-holos/synergy/change-computer-runtime)<a href="https://agentmods.dev/skills/sii-holos/synergy/change-computer-runtime"><img src="https://agentmods.dev/badge/skills/sii-holos/synergy/change-computer-runtime/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/sii-holos/synergy/change-computer-runtime"><img src="https://agentmods.dev/badge/skills/sii-holos/synergy/change-computer-runtime.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 | $0.00047 | $0.01622 |
| Opus 5.5 | $0.00019 | $0.00649 |
| Sonnet 5.5 | $0.00009 | $0.00324 |
| Haiku 4.5 | $0.00005 | $0.00162 |
Grade A, and why
change-computer-runtime 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 15d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Change Native Computer Use
Read Native Computer Use, the nearest package rules, and develop-synergy for isolation. Trace the protocol, Desktop worker, broker/tool adapter, Harness image receipts and shared UI before changing a cross-cutting behavior.
Implement and verify
- Write a failing behavioral test at the owning boundary. Keep AX and image availability independent; an observation with both channels unavailable must still preserve capture diagnostics and a recovery path. Assert that invalid or unverified images never become ordinary attachments. Exercise the actual route selected inside the native mutation lease, including semantic clicks that fall back to pixels. Trace upstream background routes for hidden activation, focus restoration and hardware-pointer use; a
backgroundargument alone does not prove non-interference. - Keep model-facing tools concise: target, returned evidence, allowed action and a useful recovery step. Translate native errors into the public tool vocabulary. Distinguish a missing OS capture grant from a window capture failure: foreground observation cannot repair missing permission. Do not import upstream agent prompts, raw native JSON or internal repair procedures into model instructions.
- Preserve exact image bytes and coordinate dimensions from capture through attachment and final provider transformation. Test the installed SDK's file/base64 and tool-result image representations as well as actual request bytes. All model-supplied coordinates share admission from the originating call's submitted image receipt; capabilities, saved files and prior calls are insufficient.
- Upgrade the official SDK and immutable worker source together. Keep local native adaptations under
apps/desktop/native/cua, preserve MIT notices and implementation provenance, build withdesktop:prepare-computer, and inspect its receipt. Both arm64 and x86_64 slices must compile; compilation alone is not execution evidence. Run native experiments in a separate source copy; never accept a build from a modified recipe cache. Regenerate the cached source from the pinned archive and owned patch before final acceptance. - Run focused Desktop Computer, Computer Runtime, Harness receipt and UI tests. Then run
desktop:test, affected type checks and rootquality:quick. Update generated contracts when public schemas change.
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.
- 15d ago Changed · +2 lines 78377ae5b58d
- 18d ago First seen · 44 lines · 47 tokens per session scan A 3ae9faf87a07
change-computer-runtime is a skill published in the GitHub repository SII-Holos/synergy (386 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 1,622 once invoked, about $0.0002 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 2026-10-01.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.