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 agentlas-ai/agentlas-desktop --skill referencegit clone --depth 1 https://github.com/agentlas-ai/agentlas-desktopWrote 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/agentlas-ai/agentlas-desktop/reference)<a href="https://agentmods.dev/skills/agentlas-ai/agentlas-desktop/reference"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/reference/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/agentlas-ai/agentlas-desktop/reference"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/reference.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 | $0.00046 | $0.11226 |
| Opus 5.5 | $0.00018 | $0.04490 |
| Sonnet 5.5 | $0.00009 | $0.02245 |
| Haiku 4.5 | $0.00005 | $0.01123 |
Grade A, and why
reference 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 14d 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 — 675 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Method and tool reference (optional)
Data-first default: acquire data, run a small exploratory experiment, inspect it and revise the hypothesis; literature proceeds in parallel. No manual read, code-index/context-impact exercise, completed review or plan approval is required for data collection, scripts or exploration. Exact provenance, honest exploratory/confirmatory labels, user stop and actual host authority still apply.
These sections used to sit in the Research Director's system prompt. They moved here unchanged (2026-09-28) so the prompt carries goals and laws only: a fixed stage order and method routes written for yesterday's models become the ceiling for better ones (Sutton, The Bitter Lesson; Chung, "Don't teach, incentivize"). The host still enforces every law and every tool's preconditions, and each refusal names its cause; read here what you need, when you need it.
Optional questions for choosing a useful next experiment
Use whichever questions clarify a real decision; they are not a checklist to complete before a tool call, table, figure or exploratory run. Prefer an available measurement to another planning pass. Do not expose them as process narration:
- When is this needed? Name the design or evidence signal that makes this operation necessary now, not merely that a capability is installed.
- What decision is live? Name the scientific fork whose alternatives would change the estimand, model, execution, interpretation, or submission package.
- What must be visible now? What must be visible for the researcher to judge that fork: the smallest exact evidence, artifact view, diagnostic, and lineage. No generic dashboard.
- What does the researcher want to do with it? What does the researcher need from this surface? Inspect, compare, choose, edit, authorize, or report. A view is not an authorization and an artifact is not an interpretation.
- What is the next action? What is the next step that connects: every displayed result leads to one valid transition, sensitivity analysis, recovery action, or manuscript task. If no supported action follows, retain the gap instead of manufacturing momentum.
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.
- 14d ago Changed · +5 lines c962db26d35f
- 18d ago First seen · 670 lines · 46 tokens per session scan A 28f546287d28
reference is a skill published in the GitHub repository agentlas-ai/agentlas-desktop (6 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 11,226 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 2026-09-29.
Other skills, from other repositories
tbtools
Use when the user asks about TBtools, TBtools-II, TBtools RPC API, TBtools CLI, or bioinformatics operations available through TBtools such as sequence manipulation, BLAST, GFF/GTF/GXF processing, expression tables, heatmaps, trees, MCScanX, DIAMOND, HMMER, MUSCLE, and IQ-TREE.
electron-expert
Expert in Electron framework, desktop app development, IPC, and cross-platform packaging. Use when the user mentions desktop, Node.js, cross platform, Windows, macOS, or Linux, or when the task involves Electron Architecture, Process Types, IPC Communication, or App Lifecycle.
autoresearch
Run an auto research / autoresearch loop for measurable improvements. Use when optimizing a skill, agent, prompt, code path, benchmark, or other target with a mechanical metric: baseline, mutate one thing, verify, keep or discard, log, chart progress, and optionally save improved custom skills or agents through Open…
architecture-diagram
How to draw and maintain the architecture diagram Ensemblr keeps for a workspace — ensemblrgetarchitecturediagram to fetch the stored one (it answers with null when nobody has drawn this workspace yet), the IR shape, how to derive it from the codebase, and ensemblrupdatearchitecturediagram to store it. Read this when…
research-orchestrator
Becomes a principal research scientist who orchestrates deep, multi-source research by coordinating evidence gathering, grading source quality, and synthesizing findings with explicit confidence levels. Use when the user needs a comprehensive research report on a complex topic, evidence-based analysis with source…
ensemblr
How Ensemblr works from inside it — the workspace/git-worktree model, the ensemblr control tools and what their answers mean, the committed .ensemblr/settings.toml (setup and run scripts, [git], [prompts], [infisical], environment variables), /.config/ensemblr/config.json, the Changes panel and diff comments, the…