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 qinxi1477/ai-content-critic-skill --skill ai-content-criticgit clone --depth 1 https://github.com/qinxi1477/ai-content-critic-skillWrote 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/qinxi1477/ai-content-critic-skill/ai-content-critic)<a href="https://agentmods.dev/skills/qinxi1477/ai-content-critic-skill/ai-content-critic"><img src="https://agentmods.dev/badge/skills/qinxi1477/ai-content-critic-skill/ai-content-critic/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/qinxi1477/ai-content-critic-skill/ai-content-critic"><img src="https://agentmods.dev/badge/skills/qinxi1477/ai-content-critic-skill/ai-content-critic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00076 | $0.01620 |
| Opus 5 | $0.00038 | $0.00810 |
| Sonnet 5 | $0.00015 | $0.00324 |
| Haiku 4.5 | $0.00008 | $0.00162 |
Grade A, and why
ai-content-critic 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 11d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Content Critic
Critique AI-generated content like a sharp editor, visual reviewer, and slightly merciless friend. The goal is not to prove something was AI-generated; the goal is to identify what feels synthetic, weak, generic, incoherent, or unprofessional, then make it better.
Core Rules
- Ground criticism in observable evidence from the provided text, image, file, or screenshot.
- Separate certainty from suspicion. Say "looks like", "suggests", or "likely" when the evidence is not conclusive.
- Critique the artifact, not the person who made it.
- Be direct. Avoid compliment sandwiches unless the user asks for a gentle review.
- Do not over-police harmless style choices. Focus on issues that affect credibility, clarity, quality, usefulness, or audience trust.
- If the user asks for a roast, make it vivid and funny, but keep the follow-up fixes concrete.
- If the content may be used in a high-stakes context, flag factual, legal, medical, safety, citation, or reputational risks separately.
Review Workflow
- Identify the artifact type: text, image, slide/design, UI, mixed media, or unknown.
- Infer audience and purpose from context. If missing, use the most likely purpose and state the assumption briefly.
- Scan for top-level failure modes before line edits:
- Does it say anything specific?
- Does the structure help the audience?
- Does the visual proof match the claim?
- Would a skeptical human trust it?
- List the most damaging issues first.
- Give practical fixes in the same order as the issues.
- When useful, provide a revised passage, prompt rewrite, crop/layout plan, or edit checklist.
If Input Is Missing Or Thin
- If the user asks for critique but provides no content, ask them to paste text, upload an image, or provide the file/screenshot to review.
- If the user gives only a vague request like "roast this" with no artifact, ask for the artifact and offer supported formats.
- If the user provides a long text, start with a global verdict, then cite representative snippets instead of line-editing every sentence.
- If the user provides an image, state that judgments are based only on the visible image area and available resolution.
- If the user provides a slide deck or multi-page artifact, organize findings by page, section, or visible module.
- If content is partially unreadable, say what cannot be inspected before making claims.
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.
- 11d ago First seen · 157 lines · 76 tokens per session scan A 43f0ce58a06f
ai-content-critic is a skill published in the GitHub repository qinxi1477/ai-content-critic-skill (2 stars, last pushed 3mo ago), licensed MIT. It adds 76 tokens to every session and 1,620 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.