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 sentimony/skills --skill negafixgit clone --depth 1 https://github.com/sentimony/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/sentimony/skills/negafix)<a href="https://agentmods.dev/skills/sentimony/skills/negafix"><img src="https://agentmods.dev/badge/skills/sentimony/skills/negafix/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/sentimony/skills/negafix"><img src="https://agentmods.dev/badge/skills/sentimony/skills/negafix.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
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 | $0.00062 | $0.05557 |
| Opus 5.5 | $0.00025 | $0.02223 |
| Sonnet 5.5 | $0.00012 | $0.01111 |
| Haiku 4.5 | $0.00006 | $0.00556 |
Grade A, and why
negafix 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 16d 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 — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.
No Negative Parallelism
Negative parallelism is the sentence shape "it's not just X, it's Y": a modest claim negated and restated grander, where the second clause adds nothing the first lacked. In classical rhetoric the figure is antithesis; in generated text it is filler that performs depth instead of delivering it. This skill bans the construction in new text and, on request, audits a project for it and scores the result.
The ban covers the construction and leaves negation itself alone. "The exporter does not compress its output" is plain factual negation and is always fine. "This isn't a date picker, it's a whole new way to think about time" is the banned shape. A sentence with a negated half and a complementary positive half is the construction whenever nobody voiced the position that the negated half rejects.
The construction inflates a claim the same way in every language, so the ban holds across languages. What changes with the language is the noise level of the detection patterns, which the Detection patterns section covers.
Write mode
Always on while this skill sits in context; applies to file edits, new files, commit messages, PR descriptions, and your own replies.
- State the claim positively, anchored in a concrete, checkable detail.
- Rewrite recipes:
- Keep the positive half and drop the negated half when the negated half carried nothing: "It's not just a formatter, it rewrites imports to the project's aliases" becomes "It rewrites imports to the project's aliases."
- A fact in the negated half survives the rewrite as its own sentence; the contrast form itself goes. "This isn't a message broker; it stores each event once and replays it on demand" becomes "It stores each event once and replays it on demand. It is not a message broker." Keep the exclusion as stated: "a durable log" drops it, and "an event store" adds a classification the original never made.
- If the second half is abstract ("transforms your workflow"), replace it with the specific fact it was gesturing at, or delete the sentence.
- If a real misconception needs correcting, name who holds it and give the correction its own sentence; that is contrast with content, and it is allowed.
- Verbatim quotations and diagnostic output inherit the
quotationverdict, and the examples in this skill inherit it too. Reproduce a violation as it stands when you report it rather than paraphrasing the evidence away.
What ships with it
6 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.
- 16d ago Changed · +3 lines e0ca536371a3
- 17d ago Changed · -180 lines 7d3603ca8d5a
- 18d ago Changed · -5 lines 9f069659cc7d
- 26d ago Changed · +1 lines 6358c4ac754c
- 1mo ago Changed · +145 lines 3a7c7addc3f9
- 1mo ago Changed · +186 lines fd04b0ccb1dd
- 1mo ago Changed · +5 tokens per session f4b873a03243
- 1mo ago Changed · +8 lines 546403b5b7cf
- 1mo ago First seen · 265 lines · 57 tokens per session scan A ad247fccb73e
negafix is a skill published in the GitHub repository sentimony/skills (6 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 5,557 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
refactor
Expert code refactoring based on Martin Fowler's catalog — improve maintainability without changing behavior. Covers code smells, composing methods, moving features, organizing data, simplifying conditionals, method calls, and generalization. Triggers on: refactor, 重构, clean up, improve code, code smell, extract…
loop-it
An automated workflow that repeatedly fetches open GitHub issues, orders them by dependencies, implements them, reviews the changes, and ships them.
walkthrough
Generate a Phase-2 Walkthrough artifact (walkthrough.md) once implementation and verification are complete. Captures a Change Summary, Verification Steps (commands + unit tests + automated browser testing outcomes), Visual Proof (screenshots/recordings embedded directly in the file), and a Review Gate (final diff + PR…
to-issues
A planning aid that breaks a PRD or technical specification into small implementation issues, each covering a complete, demonstrable piece of work.
listenhub-tts
A text-to-speech tool that uses the ListenHub service to turn written text into audio, including short recordings, multi-speaker scripts, and long-form streamed speech.
article-icons
A tool that adds static inline SVG icons from itshover.com to Markdown, HTML, and similar articles.