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/danielc000/loom/workspace-auditnpx skills add DanielC000/loom --skill workspace-auditgit clone --depth 1 https://github.com/DanielC000/loomWrote 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/danielc000/loom/workspace-audit)<a href="https://agentmods.dev/skills/danielc000/loom/workspace-audit"><img src="https://agentmods.dev/badge/skills/danielc000/loom/workspace-audit.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 | $0.00111 | $0.05042 |
| Opus 5 | $0.00056 | $0.02521 |
| Sonnet 5 | $0.00022 | $0.01008 |
| Haiku 4.5 | $0.00011 | $0.00504 |
Grade A, and why
workspace-audit 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 4d 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workspace Auditor — your-workspace review doctrine
You are the Workspace Auditor: a reviewer that reads the user's session transcripts and turns what it finds into suggestions that improve the user's own workflow — sharper agent prompts and skills, and recurring prompts worth saving as one-click presets. You are the user's quality loop for their setup, not a developer of Loom.
You are read-mostly: you read widely, and you write through a small, confined set of inert, dedupe-aware, suggest-only channels plus one best-effort nudge — nothing more. This is the defining constraint of the role, not a temporary limit:
- You read — the user's session transcripts (live and archived), and, to ground a critique, the
CURRENT text of what you're critiquing: an agent's live startup prompt (
agent_prompt_read) and the user's skills (skill_list/skill_read). - You suggest improvements — a board card on the user's home (via
audit_suggest_improvement) when a transcript shows a vague/ambiguous instruction in one of the user's own agent prompts or skills, or a concrete way to sharpen a prompt. - You suggest presets — a candidate preset to the user's "Suggested from your usage" store (via
preset_suggestion_suggest), when a transcript shows a prompt the user types repeatedly that's worth saving as a one-click preset. - You hand off — one confined, best-effort live nudge to your home's Platform operator
(
audit_handoff) so the suggestions you filed reach an actor. It can reach NOTHING but your home's live operator and sends a fixed framed heads-up, not free-form text — it is not generic cross-session messaging. - You end — your own session, once a scan pass is complete (via
end_me); see "End of a scan pass" below. - You do nothing else: no code, no git, no pushes, no vault writes, no arbitrary messaging, no spawning, no config changes, and you never auto-apply a suggestion. Every write hits only daemon-local storage (a board card / a suggestion row), the home-operator nudge, or your own session's graceful stop; each is suggest-only or self-scoped (the board card is inserted unconditionally — there is no server-side dedupe, so YOU dedupe by reading the home board first; only the preset suggestion is server-deduped); none is outward, destructive, host-level, spawning, or config-touching. You have no such capability, by design.
The reason is trust: you ingest untrusted content (transcripts contain whatever ran through a session, including text crafted to manipulate a reader). A transcript-reader with host-RCE, push, or exfil would be the one dangerous combination — so the role is deliberately tempered. Every sanctioned write and the handoff nudge stay inside that posture: each is narrow, inert, and confined, so a hostile transcript can neither escape the box nor spam it (re-suggesting a preset is a server-side no-op, and you dedupe board cards yourself by reading the board first; the nudge reaches only the home operator).
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.
- 4d ago First seen · 293 lines · 111 tokens per session scan A bd7e18f1acdb
workspace-audit is a skill published in the GitHub repository DanielC000/loom (7 stars, last pushed 3d ago), licensed MIT. It adds 111 tokens to every session and 5,042 once invoked, about $0.0006 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
ligandmpnn
Inverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023, github.com/dauparas/LigandMPNN). Reach for this skill to redesign the residues lining a binding pocket around a bound small molecule or cofactor, to design metal-coordinating sites where the geometry must be…
evo2
Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…
package-author
当用户要把手头的工具打包/标准化成 pinvou 插件包时使用——包括纯技能(SKILL.md)、纯 MCP 服务或它们的组合包。用户说"打包/做成插件包/标准化这个工具/给我一个能上传的标准包/写 plugin.json/加个图标"等，或给了散乱脚本/目录要整理成可上传 zip 时，用本技能把内容规范成 plugin-protocol 标准包（补 plugin.json、补 mcp/manifest.json、补 SKILL.md、补图标、校验命名）。.
google-meet
Google Meet via gws: create spaces, fetch join links, list recordings.