Borrowing it
Nothing to install: this file belongs to grayhatdevelopers/vidxp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/grayhatdevelopers/vidxp/main/.agents/skills/maintain-docs/SKILL.mdgit clone --depth 1 https://github.com/grayhatdevelopers/vidxpWrote 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/grayhatdevelopers/vidxp/maintain-docs)<a href="https://agentmods.dev/skills/grayhatdevelopers/vidxp/maintain-docs"><img src="https://agentmods.dev/badge/skills/grayhatdevelopers/vidxp/maintain-docs/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/grayhatdevelopers/vidxp/maintain-docs"><img src="https://agentmods.dev/badge/skills/grayhatdevelopers/vidxp/maintain-docs.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 | $0.00116 | $0.01172 |
| Opus 5.5 | $0.00046 | $0.00469 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo ago First seen · 123 lines · 116 tokens per session scan A bbc2b7aa37ca
maintain-docs is a skill published in the GitHub repository grayhatdevelopers/vidxp (59 stars, last pushed yesterday), licensed MIT. It adds 116 tokens to every session and 1,172 once invoked, about $0.0005 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 2026-08-30.
maintain-docs compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| maintain-docsgrayhatdevelopers/vidxp | Skill | 59 | yesterday | MIT | A | 116 | Codex |
| native-subtitle-quote-imagechengyi-ai/native-subtitle-quote-image | Skill | 2.9k | yesterday | MIT | A | 167 | Codex |
| video-to-skillLum1104/video-to-skill | Skill | 46 | 8d ago | MIT | A | 57 | Claude Code, Codex |
| evidence-videoheristop/leclap | Skill | 35 | 5d ago | MIT | A | 43 | Claude Code, Codex |
| authoring-video-templatesheristop/leclap | Skill | 35 | 5d ago | MIT | A | 57 | Claude Code, Codex |
| pr-evidenceheristop/leclap | Skill | 35 | 5d ago | MIT | A | 71 | Claude Code, Codex |
| core-architecture-patternsheristop/leclap | Skill | 35 | 5d ago | MIT | A | 64 | Claude Code, Codex |