ghostwrite

ghostwrite is a skill for Claude Code, Codex from runxhq/runx. It costs 24 tokens per session (862 once invoked), scanned A, original, Apache-2.0.

A writing workflow that turns checked evidence and a clear goal into publication-ready drafts or channel-specific handoff packages.

In plain words
What is it for?
Use it for briefs, release notes, maintainer updates, trust reports, newsletters, and social drafts.
Why use it?
It helps produce useful prose without exposing internal processing or filling gaps with invented facts, while leaving publication to another system.

Skill for Claude CodeCodex

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

Good fit Use it for briefs, release notes, maintainer updates, trust reports, newsletters, and social drafts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/runxhq/runx/ghostwrite
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 runxhq/runx --skill ghostwrite
Clone the repo
git clone --depth 1 https://github.com/runxhq/runx

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 ghostwrite

README.md
[![agentmods](https://agentmods.dev/badge/skills/runxhq/runx/ghostwrite/github.svg)](https://agentmods.dev/skills/runxhq/runx/ghostwrite)
Your own site
<a href="https://agentmods.dev/skills/runxhq/runx/ghostwrite"><img src="https://agentmods.dev/badge/skills/runxhq/runx/ghostwrite/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 ghostwrite

Your own site · 80×15
<a href="https://agentmods.dev/skills/runxhq/runx/ghostwrite"><img src="https://agentmods.dev/badge/skills/runxhq/runx/ghostwrite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 862 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00024 $0.00862
Opus 5 $0.00012 $0.00431
Sonnet 5 $0.00005 $0.00172
Haiku 4.5 $0.00002 $0.00086

Measured 6d ago against content hash 037e4ebc23cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ghostwrite 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (ghostwrite.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/ghostwrite/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ghostwrite

Write one bounded artifact in the voice of the human or team responsible for it. The skill turns validated evidence and a clear objective into useful public or internal prose without exposing the machinery that produced the evidence or inventing facts to make the draft feel complete.

This is the reusable authorship primitive behind briefs, release notes, trust reports, maintainer updates, newsletters, and social drafts. It can also package an accepted draft for a channel and prepare a provider-neutral handoff. It never publishes, posts, sends, or claims provider acknowledgement.

Writing standard

  • Lead with the reader's problem, decision, or next action—not the evidence collection process.
  • Turn evidence into concrete claims and examples; do not dump receipts, issue threads, graph traces, or machine packets into the body.
  • Match the project's vocabulary and supplied writing context instead of defaulting to generic AI, launch, preview, or adoption language.
  • Write as the responsible maintainer or operator. The surfaced artifact should not call itself agent-generated or narrate how a model worked.
  • Prefer one sharp, useful artifact over several thin sections.
  • Narrow the claim or return needs_more_evidence rather than filling a gap with plausible prose.

Runners and chain boundaries

draft admits a ready research or evidence packet and optionally applies digest-bound brand-voice and taste-profile context. Only admitted claims and source digests may enter the draft. Deterministic finalization verifies every material claim and every context binding before releasing it.

package converts a validated draft into a deterministic channel payload with quality checks and not_sent state. handoff records the exact target, boundary, approval need, and next actor. Neither runner grants external authority. Delivery belongs to send-as, a publication skill, or the relevant provider adapter.

Inputs and result

  • objective, audience, and channel define what the artifact must achieve.
  • The evidence input must be a validated packet with stable claim and source digests; raw assertions are not promoted into evidence.
  • Optional writing-context packets apply voice or taste. Their exact digests and only the rules actually used are recorded.
  • Packaging and handoff runners accept the validated draft or packet and the exact target metadata needed by the next boundary.

Read the full file on GitHub · 91 lines

Files

What ships with it

7 files 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. 6d ago First seen · 91 lines · 24 tokens per session scan A 037e4ebc23cd

Subscribe to this mod's changes

ghostwrite is a skill published in the GitHub repository runxhq/runx (84 stars, last pushed yesterday), licensed Apache-2.0. It adds 24 tokens to every session and 862 once invoked, about $0.0001 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 2026-09-03.