Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/odere-pro/claude-wiki-pages-pluginnpx agentmods add skills/odere-pro/claude-wiki-pages-plugin/voiceWrote 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/odere-pro/claude-wiki-pages-plugin/voice)<a href="https://agentmods.dev/skills/odere-pro/claude-wiki-pages-plugin/voice"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-wiki-pages-plugin/voice/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/odere-pro/claude-wiki-pages-plugin/voice"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-wiki-pages-plugin/voice.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 | $0.00141 | $0.02477 |
| Opus 5 | $0.00071 | $0.01239 |
| Sonnet 5 | $0.00028 | $0.00495 |
| Haiku 4.5 | $0.00014 | $0.00248 |
Grade A, and why
voice 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 9d 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Voice — how we write here
Write so a curious newcomer keeps reading and an engineer keeps trusting. Plain words for the ideas, exact words for the mechanics. Never sound like a brochure or a generated summary.
When to read this
Read it before you write or edit any prose: a README, a guide, a design doc, an ADR, a section
intro, or a wiki page. The schema in skills/init/template/CLAUDE.md
still owns frontmatter and structure; this skill owns the words. That is the schema authority — do
not cite the retired docs/vault-example/. The canonical term list is
docs/GLOSSARY.md — it wins any vocabulary question. When you name an
authoritative path in prose, it must resolve today; a stale authority path is a register failure,
not just a typo.
Pick a register by audience
Every paragraph is aimed at someone. Decide who, then pick the register.
Explanatory register — for anyone learning what the thing is or why it matters: README intros, getting-started, the guides, and the "what / why" opening of any doc. Write like you're explaining it to a sharp friend at a whiteboard.
- Short, concrete sentences. One idea each.
- Active voice. Talk to the reader as "you".
- Lead with the point, then support it. No throat-clearing.
- Show, don't label: a real example beats the word "powerful".
- A little personality is good. Dryness is not the goal; clarity is.
- Gloss a term on first use, then commit to it. The first time a glossary term appears on a page, gloss it inline in a half-sentence — "the vault (your knowledge directory)" — then use the canonical term every time after. Don't coin a synonym to dodge the term; gloss it. Spell out an acronym on first use ("Map of Content (MOC)"), then use the short form.
- One new term per sentence. Precise is not the same as dense. If a sentence needs three glossary terms, it belongs in the engineer register or wants splitting.
- Close with the one next step. End a getting-started or onboarding section by naming the single
next action —
/claude-wiki-pages:wiki, the one advertised verb — not a menu.:onboardingand:doctorare below-the-fold secondaries, never co-equal. The documented adoption failure is a section that ends with "you're set up" instead of the next verb.
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.
- 9d ago First seen · 172 lines · 141 tokens per session scan A cb766412d5dd
voice is a skill published in the GitHub repository odere-pro/claude-wiki-pages-plugin (1 stars, last pushed 2mo ago), licensed MIT. It adds 141 tokens to every session and 2,477 once invoked, about $0.0007 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
schema-evolve
This skill should be used when the user asks about 'schema drift', 'schema evolution', 'evolve schema', 'schema sync', 'sync schemas', 'update schema fields', 'schema field frequency', 'missing schema fields', 'unused schema fields', 'schema proposal', 'schema cardinality', 'check schema', 'schema audit', 'schema…
knowledge-garden
This skill should be used when the user asks to audit, health-check, or structurally validate one or more SPECIFIC named notes or a bounded topic cluster — 'audit these notes', 'check this note for orphans or broken links', 'fourth-wall check on [note]', 'validate the structure of [note]', 'spot-check [note]'. Runs a…
knowledge-maintain
This skill should be used when the user asks to fix, repair, or tidy one or more SPECIFIC named notes — 'fix these notes', 'fix the issues in [note]', 'add the missing relations to [note]', 'tidy up [note]', 'fix orphan [note]', 'apply the gardener findings for [note]'. Applies structural fixes (missing sections…
raindrop-triage
This skill should be used when the user asks to 'triage unsorted bookmarks', 'clean up raindrop inbox', 'sort unsorted', 'organize bookmarks', 'raindrop triage', 'process bookmark backlog', 'promote triaged bookmarks', 'classify triaged', 'raindrop cleanup', 'deduplicate bookmarks', 'find duplicate bookmarks', 'tag…
session-bookmarks
This skill should be used to save URLs or links found this session as Raindrop bookmarks — triggers: 'bookmark URLs from this session', 'save links we found', 'save notable URLs to Raindrop', 'save session URLs', 'raindrop bookmarks from session'. Scans the current conversation for high-signal URLs discovered during…
session-reflect
This skill should be used when the user asks to 'reflect on this session', 'save insights to memory', 'capture what we learned', 'commit this to memory', 'save decisions to Basic Memory', 'write up what we did', 'preserve what we found', 'save insights from this conversation', 'save what was discovered', 'capture…