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 JasonColapietro/suede-creator-skills --skill voice-preserving-line-editgit clone --depth 1 https://github.com/JasonColapietro/suede-creator-skillsWrote 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/jasoncolapietro/suede-creator-skills/voice-preserving-line-edit)<a href="https://agentmods.dev/skills/jasoncolapietro/suede-creator-skills/voice-preserving-line-edit"><img src="https://agentmods.dev/badge/skills/jasoncolapietro/suede-creator-skills/voice-preserving-line-edit/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/jasoncolapietro/suede-creator-skills/voice-preserving-line-edit"><img src="https://agentmods.dev/badge/skills/jasoncolapietro/suede-creator-skills/voice-preserving-line-edit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 542 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
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 | $0.00159 | $0.05856 |
| Opus 5 | $0.00079 | $0.02928 |
| Sonnet 5 | $0.00032 | $0.01171 |
| Haiku 4.5 | $0.00016 | $0.00586 |
Grade A, and why
voice-preserving-line-edit 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 9d 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 — 615 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice-Preserving Line Edit
A finishing pass for prose that is already written. It hunts throat-clearing before the point, inanimate things doing human work, binary contrasts that announce an insight instead of delivering it, and rhythm that never varies.
Two things separate this from a generic anti-slop rule sheet:
- Every rule is contextual. Adverbs, passive voice, third-person register, and em dashes are not banned outright. Each is cut only when it weakens this piece, in this genre, under this house style. A technical adverb, a conventional passive, an academic register, and a house-approved em dash all survive the pass.
- There is an audit mode. Ask for findings and you get quoted issues, reasons, and minimum corrections, with your text returned unchanged. The rewrite mode is opt-in, not the only setting.
These are writing-quality signals. They are not evidence of who or what wrote the text, and this skill never claims otherwise.
What This Skill Does
- Finds and, on request, removes filler phrases, business jargon, empty intensifiers, formulaic structures, false agency, vague declaratives, and metronomic rhythm in finished prose.
- Preserves the author's voice: deliberate fragments, dry humor, technical vocabulary, chosen formality, and useful rough edges.
- Preserves the record: facts, numbers, dates, names, prices, claims, qualifiers, quotations, code, commands, links, citations, and paths pass through untouched.
- Runs in either of two modes, findings-only audit or cleaning pass, each with its own fixed output contract.
- Scores the result on five dimensions out of 50 and returns a CLEAN or REVISE verdict about the prose quality.
What it does not do: write new copy, restructure an argument, fact-check, guess at authorship, or publish anything. See Boundaries.
When to Use This Skill
- Before copy, a README, an email, a social post, or a doc ships
- After a long AI-assisted writing session
- When the text sounds fine but feels generated
- Before anything goes to press, to investors, or to customers
- When someone wants the issues identified without a rewrite
- When a draft has to keep a specific author's voice and a generic cleanup would erase it
What ships with it
4 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.
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.
- 9d ago First seen · 615 lines · 159 tokens per session scan A 016e108e35f2
voice-preserving-line-edit is a skill published in the GitHub repository JasonColapietro/suede-creator-skills (135 stars, last pushed today), licensed MIT. It adds 159 tokens to every session and 5,856 once invoked, about $0.0008 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.
Other skills, from other repositories
skill-router
Use when a [skill-router] route card appears in the turn, when no card appeared on a non-trivial task, or when a route looks wrong. Routes every prompt to the right installed skill, pairs it with a process skill, tiers enforcement, and briefs sub-agents. 79 local skills + plugin skills indexed.
generate-report
Generate a comprehensive summary report of the latest experiment including metrics, plots, and comparison with baseline. Use this after training and evaluation to create a shareable experiment summary.
evaluate-model
Load the latest model checkpoint, run evaluation on the test set, and generate a metrics report with confusion matrix. Use this after training to assess model performance or to re-evaluate a specific checkpoint.
run-pipeline
Run the full data science pipeline: validate raw data, preprocess, engineer features, train model, and evaluate. Use this when you want to execute the end-to-end ML pipeline or re-run it after data or code changes.
api-test
Run API integration tests against the running backend, verify endpoints return expected responses and status codes. Use after deploying a preview or starting the dev server.
run-simulator
Build and launch the app in the iOS Simulator. Automatically selects an appropriate simulator device, boots it if needed, and installs and launches the app.