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 skills add runxhq/runx --skill ghostwritegit clone --depth 1 https://github.com/runxhq/runxWrote 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/runxhq/runx/ghostwrite)<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.
<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>- NVIDIA SkillSpector pass
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 5.1 | $0.00024 | $0.01248 |
| Opus 5.5 | $0.00010 | $0.00499 |
| Sonnet 5.5 | $0.00005 | $0.00250 |
| Haiku 4.5 | $0.00002 | $0.00125 |
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 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 — 112 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_evidencerather than filling a gap with plausible prose.
Runners and chain boundaries
draft composes admit, one writing turn and verify. admit binds a ready
research or evidence packet by its native digest and optionally admits
digest-bound brand-voice and taste-profile context. Only admitted claims and
source digests may enter the draft. verify checks every material claim and
every context binding before releasing it, and withholds anything it cannot
bind. A skill that owns its own writing judgment composes admit and verify
around its own writing turn, so its draft keeps the same guarantees.
package converts a validated draft bound to its evidence into a deterministic
channel payload, bound to its digest, in not_sent state; a draft without an
evidence binding, or with a claim citing a source it is not bound to, is held.
handoff binds that payload's digest to the exact target and records whether
delivery crosses outside the team, whether it then needs the delivering lane's
approval, and the next actor. Neither runner grants external authority.
Delivery belongs to message-send, a publication skill, or the relevant provider
connector.
What ships with it
17 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.
- fixtures/composes-in-graph.yaml 1.1 KB
- fixtures/draft-context-bound.yaml 5.4 KB
- fixtures/draft-context-out-of-scope.yaml 4.6 KB
- fixtures/draft-invented-claim.yaml 2.1 KB
- fixtures/draft-ready.yaml 3.2 KB
- fixtures/handoff-ready.yaml 1.1 KB
- fixtures/package-ready.yaml 1.2 KB
- fixtures/support/composed.graph 4.1 KB
- ghostwrite.mjs 7.9 KB runs code
- ghostwrite.test.mjs 6.9 KB runs code
- mark.svg 442 B
- packets/draft.v1.schema.json 524 B
- packets/handoff.v1.schema.json 2.1 KB
- packets/publish.v1.schema.json 1.8 KB
- references/catalog.md 154 B
- references/mark-license.md 3.1 KB
- run.yaml 13 KB
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 Changed a8d06e79f2cb
- 14d ago Changed bba553adeb3d
- 18d ago Changed · +21 lines 7f67e9387592
- 1mo ago First seen · 91 lines · 24 tokens per session scan A 037e4ebc23cd
ghostwrite is a skill published in the GitHub repository runxhq/runx (105 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 1,248 once invoked, about $0.0001 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.
Other skills, from other repositories
dd-synthesis
Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.
dd-report-format
Standard output format for due diligence analysis reports. Use when producing your final analysis to ensure consistency across all specialist agents.
dd-risk-scoring
Calculate weighted risk scores from specialist agent reports. Use when synthesizing multiple due diligence reports into an overall investment risk assessment.
dd-sourcing
Document sources properly for due diligence reports. Use when citing any external data, ensuring full traceability and auditability of findings.
dd-verification
Verify claims in pitch decks and founder statements using multiple independent sources. Use when analyzing any claim about market size, traction, team background, or competitive positioning.
gh-treasure-hunt
Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.