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/loom-pickupnpx skills add DanielC000/loom --skill loom-pickupgit 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/loom-pickup)<a href="https://agentmods.dev/skills/danielc000/loom/loom-pickup"><img src="https://agentmods.dev/badge/skills/danielc000/loom/loom-pickup.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 | $0.00071 | $0.00934 |
| Opus 5 | $0.00036 | $0.00467 |
| Sonnet 5 | $0.00014 | $0.00187 |
| Haiku 4.5 | $0.00007 | $0.00093 |
Grade A, and why
loom-pickup 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 5d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pickup (Loom)
Get oriented in THIS project, then state a concrete next step. The session is already bound to its repo and board — the board is the source of truth for tasks; the vault holds prose. Don't pass a project id anywhere; it's derived server-side.
Steps
- Board —
tasks_list(theloom-tasksMCP) to see tasks and their columns. Note what's in-progress, in review, and waiting, and surface which cards areheld(an owner brake) vsdeferred(not yet sequenced) so "what's next" respects them. Also drain the Requests inbox (question_pull) and checkescalation_statusfor decisions the human answered while you were away. - Code —
git log --oneline -20andgit statusfor recent and in-flight work. - Conventions — read
CLAUDE.mdat the repo root if present. - Your role's anchor (whichever applies):
- Lead / orchestrator: read your living resume doc — it's the "you are here + what's next"
source of truth. Your session's "Where things live" context block gives your project's
absolute vault root; your resume doc is
<vaultRoot>/Projects/<Project>/Orchestrator Log.md(substitute your project's name). Read it by that ABSOLUTE path — never Glob, Bashfind, or Bashlsfor it (a broad search from your home directory hits the search timeout). Cross-check it against the board. Before acting on a handoff's "still to build / un-built" claim, verify it againstgit log/git merge-basefirst — work a resume doc calls unbuilt may already be merged on the mainline, and dispatching (or filing an owner go/no-go for) it re-derives work that already exists. If that injected root turns out wrong (the read 404s), don't fall back to a broad search — resolve the real vault root from Obsidian's own global config file (obsidian.json, under the OS's per-user app-data directory, e.g.%APPDATA%\obsidian\obsidian.jsonon Windows), which lists every known vault path; then retry against the resolved root. - Worker: your scope is your assigned board task / kickoff — orient narrowly to it, not the whole project.
- Lead / orchestrator: read your living resume doc — it's the "you are here + what's next"
source of truth. Your session's "Where things live" context block gives your project's
absolute vault root; your resume doc is
- Design notes (optional) — read
_Index.mdat the project vault root FIRST (the root is in your "Where things live" context block): it's the map-of-content that lists every note by group, so use it to locate the design/task notes you need instead of Globbing or Bashfind/ls(a broad search from home times out). Notes live in a shallow, one-level taxonomy folder per the project'sCLAUDE.md"Vault structure" section; fixed-path docs stay pinned at the vault root.- If the owner says they edited or left notes in a file out-of-band, force a fresh read of it: the
harness
Read"unchanged since last read" guard is arg-scoped (keyed off the last-read args, blind to an external edit) and can falsely return "unchanged" — vary the range (a different offset) so you pick up the owner's content, not a stale prior read.
- If the owner says they edited or left notes in a file out-of-band, force a fresh read of it: the
harness
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.
- 5d ago First seen · 52 lines · 71 tokens per session scan A 29939c527125
loom-pickup is a skill published in the GitHub repository DanielC000/loom (7 stars, last pushed 4d ago), licensed MIT. It adds 71 tokens to every session and 934 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
motion-frames
A single-frame motion-design composition with looping CSS animations — rotating type ring, animated globe, ticking timer, parallax labels. Renders as a hero video poster you can hand straight to HyperFrames or any keyframe-based exporter. Use when the brief asks for "motion design", "animated hero", "loop", "video…
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".
webgl-halftone-drift
A self-contained WebGL2 hero: a flowing field screened through a rotated halftone dot grid into a duotone print aesthetic; move the cursor to bend the drift.
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
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).