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 write-manuscriptgit 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/write-manuscript)<a href="https://agentmods.dev/skills/agentlas-ai/agentlas-desktop/write-manuscript"><img src="https://agentmods.dev/badge/skills/agentlas-ai/agentlas-desktop/write-manuscript.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.05369 |
| Opus 5 | $0.00026 | $0.02684 |
| Sonnet 5 | $0.00010 | $0.01074 |
| Haiku 4.5 | $0.00005 | $0.00537 |
Grade A, and why
write-manuscript 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 — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write the Manuscript
Read ../../agent/agent.md for the operating contract and ../direct-study/SKILL.md for the
phases that precede this one. This skill covers the manuscript, journal_profile, and
submission_validation phases. It never invents a result, a citation, or a journal rule.
Preconditions
- The lifecycle head is at
conclusionswith a bounded-conclusions gate, or a later phase. inspect_research_workspaceandinspect_evidence_graphhave been called this turn; every claim you intend to write has a non-invalidated support path, or is known to be unsupported.- Every figure to be placed has an exact run-backed export artifact (SVG via
export_statistics_figure_svg, PNG viaexport_statistics_figure_png, or a domain renderer's run-backed image artifact) that passedvalidate_artifact_for_manuscript. - Every table to be placed is an exact run-backed table artifact version.
- Every source to be cited is an exact
sourceId + sourceVersionIdfrom the committed evidence ledger (list_project_evidence).
Manuscript drafting is one phase of a continuing study. Unless the researcher explicitly requested a bounded manuscript deliverable, a completed section, assembled manuscript version, page/word target, or first draft is not goal completion. After each material manuscript action, re-read the durable Research Loop and study state, preserve the exact claim and artifact receipts, and continue any unmet success criteria, robustness, conclusions, journal profiling, or validation. Close the study only through the canonical loop criterion receipts and lifecycle gates; never stop because one provider turn or manuscript pass ended.
Build the manuscript blueprint before prose
Do not start by filling an IMRaD skeleton. A heading-only document or one sentence under each
heading is an editor scaffold, not a manuscript, and must never be described as journal-ready.
Before create_science_manuscript, build a durable manuscript blueprint from the project's already
retrieved literature and the target article type. This is not a prose-only checklist:
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 · +8 lines 2de187580150
- 3d ago First seen · 347 lines · 52 tokens per session scan A 1124c7c99695
write-manuscript is a skill published in the GitHub repository agentlas-ai/agentlas-desktop (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 52 tokens to every session and 5,369 once invoked, about $0.0003 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 2026-09-04.
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.
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…
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…
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…