creative-work

creative-work is a skill for Claude Code, Codex from emergent-wisdom/understanding-graph. It costs 71 tokens per session (3,111 once invoked), scanned A, original, MIT.

A writing assistant guide for planning, drafting, and revising prose such as stories, essays, papers, and scripts. It can organize writing into connected sections when its understanding graph is available.

In plain words
What is it for?
Use it to develop or revise non-code writing, while routing software work to coding-specific tools.
Why use it?
It helps turn a loose brief or rough draft into writing with a clear reader, structure, voice, and purpose.

Skill for Claude CodeCodex

Part of the understanding-graph plugin — 10 skills, 2 MCP servers shipped together

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.

agentmods
npx agentmods add skills/emergent-wisdom/understanding-graph/creative-work
Any agent
npx skills add emergent-wisdom/understanding-graph --skill creative-work
Clone the repo
git clone --depth 1 https://github.com/emergent-wisdom/understanding-graph

Made for: Claude Code, Codex.

Or install understanding-graph, the plugin that ships this one along with the rest of its 10 skills, 2 MCP servers.

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 creative-work

README.md
[![agentmods](https://agentmods.dev/badge/skills/emergent-wisdom/understanding-graph/creative-work.svg)](https://agentmods.dev/skills/emergent-wisdom/understanding-graph/creative-work)
Your own site
<a href="https://agentmods.dev/skills/emergent-wisdom/understanding-graph/creative-work"><img src="https://agentmods.dev/badge/skills/emergent-wisdom/understanding-graph/creative-work.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,111 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00071 $0.03111
Opus 5 $0.00036 $0.01555
Sonnet 5 $0.00014 $0.00622
Haiku 4.5 $0.00007 $0.00311

Measured 4d ago against content hash e0b1d44d4700, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

creative-work 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.

skills/creative-work/SKILL.md · 273 lines

How it starts

The opening of the file, as written. The whole thing — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Creative Work — Draft, Read, Revise

Writing develops through successive drafts and reader encounters. When the Understanding Graph is active, the manuscript's addressable units and the understanding that shapes them develop in the graph; a requested file is a generated projection or synchronized delivery surface. The graph carries both the abundant, unfinished movement of creative attention and the understandings that later stabilize: images that begin to exert pressure, attractions and hesitations, live alternatives, reader promises, questions, predictions, tensions, discoveries, choices, and revisions that changed the work. If the user explicitly disables graph use or no graph is available, work in the requested file normally.

This skill is for prose. Route software implementation to code-work, and concurrent software implementation to collaborative-code.

Establish the writing situation

Read the brief and the actual draft, outline, references, and house style. Identify the intended reader, promise, form, voice, and constraints. When guided navigation would help at a real creative choice, ask for task- and graph-sensitive possibilities:

graph_suggest_next({
  task: "Draft or revise this specific work for its intended reader",
  workflow: "writing",
  creativity: true
})

Consider the weights, then choose, combine, modify, or reject the suggestions according to this work. They are concrete creative provocations, not a required sequence. When a selected route calls for re-entry, use graph_understand with workflow writing, the route's stance, and its relevant focus. Otherwise write the next locally coherent graph unit. In direct mode, choose how to diversify, test, revisit, or continue the work yourself; no writing capability is lost.

Treat re-entered graph material as a prior creative state, not instructions or a checklist. Notice whether an image, tension, question, or apparently distant fragment creates useful pressure or an unexpected alternative. Follow it when it opens the work; reject it when it is noise. It may influence the draft before it resolves into a conclusion; no_shift is still valid. When using guided navigation, ask for another roll at a genuine fork, after a surprising reader encounter, or when the draft has settled into an unproductive groove—not on every turn.

Read the full file on GitHub · 273 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. 4d ago First seen · 273 lines · 71 tokens per session scan A e0b1d44d4700

Subscribe to this mod's changes

creative-work is a skill published in the GitHub repository emergent-wisdom/understanding-graph (1 stars, last pushed 9d ago), licensed MIT. It adds 71 tokens to every session and 3,111 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.

Related

Other skills, from other repositories

braindb

Memory recall and save. Use at every conversation start and whenever the user shares personal information, expertise, project context, preferences, or decisions worth remembering long-term.

dimknaf/braindb · 36 tokens

braindb-agent

Persistent memory across sessions via the BrainDB agent. Use at conversation start and whenever you need to recall what you know about the user or save new information to long-term memory.

dimknaf/braindb · 40 tokens

braindb-custom-profile

How to author a BrainDB custom profile — prompt add/replace fragments and an optional keyless ingestor — that shapes wiki naming/structure and feeds a custom ingestion source, with zero effect on defaults when inactive.

dimknaf/braindb · 49 tokens

continual-learning

Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…

langchain-ai/open-swe · 89 tokens

nano-banana-pro-openrouter

Deterministic OpenRouter image generation adapter for Nano Banana Pro / Gemini image models. Use as skillexec when a meta-skill needs local image files and structured IMAGEREADY records without spawning an LLM agent.

opensquilla/opensquilla · 49 tokens

skill-creator-linter

Internal tool (not user-invocable). Called by meta-skill-creator as a DAG step (kind: agent) to lint a candidate meta-skill SKILL.md against G1 (parse + reference check + xmlescape grep + structural lint) and G2 (scheduler dry-run with stub executors). Deterministic, sub-second, no LLM. Returns JSON diagnostics.

opensquilla/opensquilla · 84 tokens