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 agentmods add skills/grayhatdevelopers/vidxp/maintain-docsnpx skills add grayhatdevelopers/vidxp --skill maintain-docsgit clone --depth 1 https://github.com/grayhatdevelopers/vidxpWhat 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 | $0.00116 | $0.01172 |
| Opus 5 | $0.00058 | $0.00586 |
| Sonnet 5 | $0.00023 | $0.00234 |
| Haiku 4.5 | $0.00012 | $0.00117 |
Grade A, and why
maintain-docs 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 2d 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain VidXP documentation
Keep VidXP documentation accurate, appropriately placed, and readable without requiring the reader to know the implementation first.
Load the project context
-
Read the applicable
AGENTS.mdinstructions anddocs/CONTRIBUTING.md. -
Read references/documentation-map.md to identify the document owner and audience.
-
Read references/writing-standard.md before creating, rewriting, or reviewing human-facing prose.
-
Inspect
git statusand the relevant diff. Preserve unrelated work and do not stage or commit changes unless the user asks. -
Run the established Markdown checks before editing to record the baseline:
npx --yes [email protected] lychee "**/*.md" ".github/**/*.md" ".agents/**/*.md"If Lychee is unavailable locally, use the pinned container command in
docs/CONTRIBUTING.mdor report that the link check was not run. Record the baseline instead of attributing pre-existing findings to the current change.
Maintain the documentation
1. Define the change
- Identify the behavior, decision, workflow, or correction being documented.
- Determine whether the task concerns one document, the current diff, or a wider documentation audit.
- Identify every affected surface: end user, integrator, operator, contributor, maintainer, researcher, or agent.
Do not treat an audience label as proof that prose is suitable for that audience. Evaluate the document's vocabulary, sequence, assumptions, and level of detail.
2. Choose the owner
- Update the smallest document that owns the information.
- Link to the canonical explanation instead of copying it into several files.
- Use tutorial, how-to, reference, and explanation as reader-need categories, not as a mandatory directory structure.
- Keep human contributor guidance separate from agent instructions.
- Keep repository-maintenance guidance separate from the product-distributed
skills under
plugins/vidxp/skills/. - Do not create a documentation changelog, decision log, incident report, or new directory taxonomy unless the repository has adopted it or the user asks.
What ships with it
3 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.
- 2d ago First seen · 123 lines · 116 tokens per session scan A bbc2b7aa37ca
maintain-docs is a skill published in the GitHub repository grayhatdevelopers/vidxp (30 stars, last pushed 2d ago), licensed MIT. It adds 116 tokens to every session and 1,172 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
native-subtitle-quote-image
将本地视频或用户有权处理的在线视频,经过来源获取、文字稿定位、选题选句、精确取帧、紧凑裁切、3:4 拼图和逐张质检,制作成视频字幕社交长图。支持两种明确分开的输出:保留画面内已烧录字幕的原生字幕模式,以及把已审核的时间点与台词绘制到真实视频帧上的脚本字幕模式。用户要求原生字幕截图、字幕帧拼图、YouTube 金句长图、台词截图、不重绘字幕、自定义中文台词,或调整主图比例、字幕区域、台词间隔和美感时使用。.
authoring-video-templates
Use when creating or editing a video template JSON (the template descriptor), adding or changing sections/filters/maps/variables/transitions/looks/motion/audio/layers, or debugging template validation errors in ffmpeg-video-composer.
reflectworld-percept
Perception automatically analyzes video segments from Eye using cloud VLM (Gemini). Working Memory tracks cross-segment event context. Results flow to ReflectWorld (storage) and Act (rules) via PostProcessor — all automatic.
reflectworld
You have access to ReflectWorld, a visual perception and persistent memory system. It gives you eyes and memory for cameras.
reflectworld-mem
Search and manage ReflectWorld video memories from ReflectWorld cameras.
core-architecture-patterns
Use when adding a segment type, platform adapter, editor manager, core service, or descriptor effect (look/grade/motion/section-audio field) in packages/ffmpeg-video-composer, or when wiring new dependencies into the tsyringe container.