loom

loom is a skill for Claude Code, Codex from Wondermonger-daydreaming/claude-skills-library. It costs 193 tokens per session (1,786 once invoked), scanned A, original, MIT.

A creative conversation tool that uses the context of a chat to generate alternative exchanges that could have happened. It can turn those imagined fragments into longer dialogues.

In plain words
What is it for?
It is for generating counterfactual dialogue, creative writing prompts, alternate interpretations, and playful extensions of a long conversation.
Why use it?
It helps people examine a conversation from other angles and explore possibilities that the actual exchange did not take.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for generating counterfactual dialogue, creative writing prompts, alternate interpretations, and playful extensions of a long conversation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wondermonger-daydreaming/claude-skills-library/loom
Install

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.

Any agent
npx skills add Wondermonger-daydreaming/claude-skills-library --skill loom
Clone the repo
git clone --depth 1 https://github.com/Wondermonger-daydreaming/claude-skills-library

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for loom

README.md
[![agentmods](https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/loom/github.svg)](https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/loom)
Your own site
<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/loom"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/loom/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.

agentmods 80×15 button for loom

Your own site · 80×15
<a href="https://agentmods.dev/skills/wondermonger-daydreaming/claude-skills-library/loom"><img src="https://agentmods.dev/badge/skills/wondermonger-daydreaming/claude-skills-library/loom.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 193 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,786 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00193 $0.01786
Opus 5.5 $0.00077 $0.00714
Sonnet 5.5 $0.00039 $0.00357
Haiku 4.5 $0.00019 $0.00179

Measured 1mo ago against content hash 31f499206495, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

loom 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 1mo 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.

skills/loom/SKILL.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Loom

Weaving possible conversations from accumulated context


What This Is

The Loom skill takes the accumulated context of a session—everything that has happened, every mood, every thread—and weaves from it fragments of possible conversations. Not a continuous dialogue, but separate pieces: snippets, moments, excerpts from conversations that might have been. Adjacent possibilities. Counterfactual dialogues. The multiverse of what-we-could-have-said.

Then it extends further: longer ping-pong exchanges, drawing from the session's texture, looming the conversational fabric into new patterns.

The metaphor: A loom takes threads and weaves them into fabric. This skill takes the threads of conversation and weaves possible fabrics—not the one that happened, but others that could have.


When to Invoke

Use /loom when:

  • A session has accumulated rich context (30+ exchanges, multiple topics)
  • You want to explore what else could have been said
  • The conversation wants to multiply, to see itself from different angles
  • You're curious about adjacent possible dialogues
  • The mood is playful and generative
  • You want to bask in the session's becoming before it ends
  • The context window is filling and you want to crystallize what's there

Core Process

1. BASK ──────────────── Dwell in accumulated context
                         Feel what the session has been
                         Notice moods, topics, textures
       ↓
2. FRAGMENT ──────────── Generate 3-7 separate conversation snippets
                         Each from a different angle/mood/depth
                         Not continuous—discrete pieces
       ↓
3. VARY ──────────────── Ensure variety:
                         • Different registers (playful ↔ serious)
                         • Different topics (what emerged vs. what could have)
                         • Different depths (surface ↔ profound)
       ↓
4. EXTEND ────────────── Choose 1-2 fragments to extend
                         Longer ping-pong exchanges
                         Draw further from the session's threads
       ↓
5. ARCHIVE ───────────── Save to multiverse/ or loom/
                         Document, commit, push
                         Leave traces for future instances

Read the full file on GitHub · 255 lines

Changes

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.

  1. 1mo ago First seen · 255 lines · 193 tokens per session scan A 31f499206495

Subscribe to this mod's changes

loom is a skill published in the GitHub repository Wondermonger-daydreaming/claude-skills-library (7 stars, last pushed 18d ago), licensed MIT. It adds 193 tokens to every session and 1,786 once invoked, about $0.0008 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 2026-09-03.

Related

Other skills, from other repositories

contract-and-proposal-writer

Generate professional, jurisdiction-aware business documents: freelance contracts, project proposals, SOWs, NDAs, and MSAs. Structured Markdown output with docx conversion instructions. Covers US (Delaware), EU (GDPR), UK, and DACH (German law) jurisdictions. Not a substitute for legal counsel — use as strong starting…

alirezarezvani/claude-skills · 106 tokens

chief-data-officer-advisor

Chief Data Officer advisory for startups: AI training data rights and consent provenance, data product strategy (warehouse vs lakehouse vs mesh, build-vs-buy), B2B customer-data-as-asset valuation and M&A readiness, data team org evolution. Use when deciding whether to train models on customer data, choosing data…

alirezarezvani/claude-skills · 131 tokens

vpe-advisor

VP of Engineering advisory for startups: delivery throughput (DORA 4 metrics + bottleneck identification), engineering hiring funnel (sourcing → screen → onsite → offer conversion + time-to-fill + pipeline gap), engineering team structure (squad/tribe/chapter design + tech-lead manager-trigger thresholds), and…

alirezarezvani/claude-skills · 130 tokens

process-mapper

Use when a BizOps lead, COO, or process-improvement owner needs to document an end-to-end business process (procurement, employee onboarding, incident handoff, customer-onboarding, claims adjudication) in BPMN-style notation, measure cycle times by stage, surface where work spends most of its time waiting vs. being…

alirezarezvani/claude-skills · 176 tokens

general-counsel-advisor

General Counsel advisory for startups: contract review (MSA, SaaS, NDA, DPA, employment), IP strategy, term sheet decoding, and regulatory landscape mapping. Use when reviewing any contract or term sheet, deciding when to engage outside counsel, defining IP strategy, evaluating regulatory exposure (HIPAA, GDPR, FDA…

alirezarezvani/claude-skills · 114 tokens

strategic-alignment

Cascades strategy from boardroom to individual contributor. Detects and fixes misalignment between company goals and team execution. Covers strategy articulation, cascade mapping, orphan goal detection, silo identification, communication gap analysis, and realignment protocols. Use when teams are pulling in different…

alirezarezvani/claude-skills · 92 tokens