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 rretsiem/opencode-hive --skill wiki-lintgit clone --depth 1 https://github.com/rretsiem/opencode-hiveWrote 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/rretsiem/opencode-hive/wiki-lint)<a href="https://agentmods.dev/skills/rretsiem/opencode-hive/wiki-lint"><img src="https://agentmods.dev/badge/skills/rretsiem/opencode-hive/wiki-lint/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/rretsiem/opencode-hive/wiki-lint"><img src="https://agentmods.dev/badge/skills/rretsiem/opencode-hive/wiki-lint.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 | $0.00055 | $0.00423 |
| Opus 5.5 | $0.00022 | $0.00169 |
| Sonnet 5.5 | $0.00011 | $0.00085 |
| Haiku 4.5 | $0.00006 | $0.00042 |
Grade A, and why
wiki-lint 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 1mo 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.
What it actually says
Wiki Lint
When to Use
- "Check the wiki health"
- "Lint the wiki"
- "Are there stale wiki pages?"
- After major refactors
- Monthly maintenance
Workflow
- Invoke the wiki-curator agent with the lint operation.
- The curator runs the conformance checklist from
WIKI_SCHEMA.md:- Parseable YAML frontmatter on every non-reserved
.mdfile - Non-empty
type:on every concept index.mdandlog.mdfollow their structure when presentsources[].idis unique per concept- Markdown footnote labels match a
sources[].id stale_afteris an ISO date when present- Cross-references resolve or are flagged as future-writes
- Parseable YAML frontmatter on every non-reserved
- The curator marks stale pages (
⚠️ STALE — past stale_after (<date>)or⚠️ STALE — last verified <date>) at the top of the body. - Report findings categorized by severity (critical / warning / note).
- Ask the user which issues to fix automatically vs flag for manual review.
Notes
- OKF v0.2 is permissive: missing optional fields, unknown types, unknown extra frontmatter keys, and broken cross-links are warnings, not failures.
- A missing
type:field is the only conformance failure that prevents a bundle from being consumable. - Trust tiers are advisory. A wiki without
verified:entries is still consumable; consumers just classify such pages as "unverified".
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.
- 1mo ago First seen · 40 lines · 55 tokens per session scan A 49420d675f9c
wiki-lint is a skill published in the GitHub repository rretsiem/opencode-hive (42 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 423 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 2026-08-30.
Other skills, from other repositories
guashuai
An orchestrator mode that divides a large coding task into separate jobs and assigns them to worker agents that can run in parallel.
junshi
An advisor mode in which the main, lower-cost agent does everyday work and asks a stronger helper agent for occasional advice on difficult decisions.
pandic-office
Convert Markdown to PDF (or DOCX/EPUB/HTML) using the pandoc CLI. Use when asked to produce a PDF report, brief, summary, or any document where the input is Markdown and the output should be a polished, paginated file.
tmux
Manage long-running shell sessions with tmux — start a detached session, run a long task, reattach later, capture output. Use when a task takes longer than a single tool call (build, test, log tail).
web-research
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research.
pptx
Instructions for reading, creating, and editing PowerPoint presentation files and templates, including .pptx, .potx, and older .ppt files. They cover text, tables, images, charts, layouts, and speaker notes.