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/cloudguo123/atomlane/accelerate-local-worknpx skills add cloudguo123/atomlane --skill accelerate-local-workgit clone --depth 1 https://github.com/cloudguo123/atomlaneWrote 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/cloudguo123/atomlane/accelerate-local-work)<a href="https://agentmods.dev/skills/cloudguo123/atomlane/accelerate-local-work"><img src="https://agentmods.dev/badge/skills/cloudguo123/atomlane/accelerate-local-work.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 5.1 | $0.00082 | $0.04303 |
| Opus 5 | $0.00041 | $0.02152 |
| Sonnet 5 | $0.00016 | $0.00861 |
| Haiku 4.5 | $0.00008 | $0.00430 |
Grade A, and why
accelerate-local-work 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 — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AtomLane: Accelerate Local Work
AtomLane parallelizes only what is proven safe. Preserve task semantics first: parallelism is legal only when the compiled control flow, effects, resources, and authorization boundaries prove it safe.
Perform a cheap preflight
Use this skill when at least one condition holds:
- A composite command, package script, Make target, Compose application, test suite, or build pipeline may contain independent work.
- One meaningful operation repeats across independent inputs.
- A dependency graph has two or more potentially ready nodes.
- A numerical, image, signal, ML, video, compression, or custom-GPU operation may use an Apple-silicon backend.
Skip it for conversation, web research, one quick command, tiny work dominated by startup, or a known fully serial mutation. Evaluation should be cheap; the possibility of parallelism alone does not authorize execution.
If the requested optimization requires changing a long-running Python program
rather than scheduling its existing commands, route to
$optimize-python-parallelism and python_parallel_advisor. Do not treat a
source rewrite preview as an executable atomic plan.
Identify the execution realm before compiling. Native Windows, one WSL distro,
and one Docker daemon are distinct resource and path spaces; never mix them in
one plan without an explicit bridge. On native Windows Preview, use exact argv
atoms or the whole-file powershell_file adapter. POSIX shell, package-script,
Make-recipe, and Compose lowering are not Windows semantics and must fail
closed. Do not lower inline PowerShell or cmd/.bat syntax.
Compile once, execute the exact plan
For local execution covered by this skill, use this invariant:
atomic_task_plan -> immutable compiled_plan + plan_hash -> atomic_exec
- Call
atomic_task_planbefore the first execution batch. Supply the active project, task intent, and concrete entrypoints or candidate operations known at that point. Usescenario_planfirst only when an unfamiliar multi-stage project, preset optimization profile, or explicitly requested trace evidence would materially improve planning. For one concrete pytest suite, prefertest_suite_plan; it is a thin frontend that returns the same standard immutable plan and does not create a separate execution path. - Inspect the returned blockers, diagnostics, effect certainty, native
delegates, resource plan, estimated benefit, and
plan_hash. Do not execute a plan that reports an unresolved safety blocker. - Treat the complete return value as
compiled_plan. Pass that exact object and its hash toatomic_exec:
What ships with it
2 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.
- yesterday Changed · +142 lines · -7 tokens per session 93542670c09b
- 5d ago First seen · 208 lines · 89 tokens per session scan A d9d44080d72e
accelerate-local-work is a skill published in the GitHub repository cloudguo123/atomlane (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 82 tokens to every session and 4,303 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
apple-container
Build, run, and manage OCI/Linux containers as lightweight per-container VMs on Apple-silicon macOS using Apple's open-source container CLI, no Docker daemon required.
benchmark
Run performance + quality benchmarks. ASR reports WER, RTF, process memory, and throughput across engines/variants. Arguments include asr, tts, vad, diarize, asr-quick.
review-pr
Review a pull request for conceptual fit, architecture impact, adversarial failure modes, security risk, docs impact, regression risk, test coverage, and merge readiness. Use when asked to review a PR, check whether a PR is safe to merge, decide if more tests are needed, perform adversarial or security review, or…
test
Run tests. Use after code changes to validate. Arguments: unit (default, no GPU), e2e (with models), filter name, or all.
vocello-design
Use this skill to generate well-branded interfaces and assets for Vocello (a local-first, Apple-native macOS voice-generation app — formerly QwenVoice). Contains essential design guidelines, colors, type, fonts, assets, and a Mac-app UI kit for prototyping voice-studio interfaces, marketing surfaces, and slides.
macvis
On-device, zero-token vision for AI agents (mac-local-vision, macOS). Read text from an image / screenshot / PDF (OCR), find the exact click-pixel of a word for E2E/UI assertions, scan QR codes and barcodes, tag/classify an image, group photos by face, flatten a photographed document, extract a document's structured…