create

A writing-focused tool for creating a new NeatContext profile from a user’s behavior rules and an existing folder of knowledge. NeatContext is a named set of instructions and reference material that guides future work.

In plain words
What is it for?
Use it to create a context profile, distinguish it from existing contexts, and save the resulting draft for review.
Why use it?
It turns scattered guidance and local reference files into a reusable context with a clear purpose and routing description.

Skill for Claude CodeCodex

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/xtsoftwarelabs/neatcontext-plugins/create
Any agent
npx skills add XTSoftwareLabs/neatcontext-plugins --skill create
Clone the repo
git clone --depth 1 https://github.com/XTSoftwareLabs/neatcontext-plugins

Made for: Claude Code, Codex.

Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 425 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 $0.00045 $0.00425
Opus 5 $0.00023 $0.00212
Sonnet 5 $0.00009 $0.00085
Haiku 4.5 $0.00005 $0.00042

Measured 2d ago against content hash 8e688842d3d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create 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 2d 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.

codex-marketplace/plugins/neatcontext/skills/create/SKILL.md · 39 lines

What it actually says

Create context

Resolve <plugin-root> as two directories above the directory containing this file.

Keep this workflow distinct from $neatcontext:save: create starts from user-provided purpose and existing knowledge; save distills work already in the conversation.

Collect these inputs, asking one question at a time only for information the user has not already supplied:

  1. What the context covers, what Codex should do and avoid, and how it should behave.
  2. The path to an existing folder containing its knowledge.
  3. A short context name.

Run list before drafting so the routing description can distinguish adjacent contexts:

node "<plugin-root>/src/codex/neatcontext-cli.mjs" list

Draft a Markdown profile beginning with # <name> and containing ## Purpose, ## What to do, ## What to avoid, and ## Behavior. Preserve the user's meaning and add no unsupported rules.

Draft one routing description under 200 characters. Describe scope only, using systems, symptoms, repos, ticket prefixes, and terminology someone would type. Make it contrastive with existing contexts. Do not include tone, behavior, or output-format instructions.

Show both drafts and wait for confirmation.

After confirmation, write the profile to a unique temporary Markdown file. Prefer a host scratch directory; otherwise use the workspace and remove the file after the CLI finishes. Run:

node "<plugin-root>/src/codex/neatcontext-cli.mjs" create --name "<name>" --knowledge "<folder>" --profile-from "<profile-file>" --use-when "<routing-description>"

Pass each value as one argument. On Windows, remove a trailing backslash from the knowledge-folder argument before quoting it.

Relay the result and remove only the temporary profile file. Do not connect the new context automatically.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 39 lines · 45 tokens per session scan A 8e688842d3d4

Subscribe to this mod's changes

create is a skill published in the GitHub repository XTSoftwareLabs/neatcontext-plugins (13 stars, last pushed 9d ago), licensed MIT. It adds 45 tokens to every session and 425 once invoked, about $0.0002 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 2026-08-30.