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/markdownWrote 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/markdown)<a href="https://agentmods.dev/skills/odere-pro/claude-wiki-pages-plugin/markdown"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-wiki-pages-plugin/markdown.svg" alt="Measured on agentmods" 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 | $0.00094 | $0.01620 |
| Opus 5 | $0.00047 | $0.00810 |
| Sonnet 5 | $0.00019 | $0.00324 |
| Haiku 4.5 | $0.00009 | $0.00162 |
Grade A, and why
markdown 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 8d 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.
LLM Wiki — Markdown export
Run a query against vault/wiki/, render the answer as portable markdown,
and write it to vault/output/<slug>.md. The result is plain
GitHub-flavored markdown — no [[wikilinks]], no Dataview blocks, no
Obsidian callouts — suitable for pasting into a PR body, an email, or a
non-Obsidian doc tool.
This skill is the publish-side counterpart to /claude-wiki-pages:query.
Query stays in the conversation; markdown lands on disk.
When to invoke
- The user explicitly asks to export, save, or render an answer as markdown ("export this as markdown", "save to the output folder").
- The user invokes
/claude-wiki-pages:markdowndirectly. - An agent (
claude-wiki-pages-analyst-agentCompile mode) chains this skill as a step.
Do NOT invoke when the user just wants an answer in the chat — use
/claude-wiki-pages:query for that.
Do NOT invoke for synthesis notes (cross-topic analyses live under
wiki/_synthesis/) — use /claude-wiki-pages:synthesize.
Reading contract
Same order and scope as /claude-wiki-pages:query:
vault/CLAUDE.md— the schema. Read first.vault/wiki/index.md— the top-level catalog.vault/wiki/<topic>/<topic>.md— per-folder MOCs (folder notes; legacy_index.mdwhere still present).vault/wiki/<topic>/*.md— candidate typed pages, plus pages reached by following[[wikilinks]](one hop) when the answer needs them.vault/wiki/_synthesis/*.md— prior syntheses, if relevant.vault/wiki/_sources/*.md— source summaries, when provenance matters.
Rendering contract
Convert wiki-flavored markdown to portable markdown:
- Wikilinks — replace
[[Page Title]]with[Page Title](../wiki/<path>/<slug>.md)(relative path fromvault/output/) when the target page resolves. If the target does not resolve, drop the link syntax and keep the plain text — never emit a dangling[[link]]. - Callouts — convert
> [!note] Titleand similar to a regular blockquote with the title bolded (> **Title**on the first line, then> body…on the next). - Dataview blocks — strip fenced
```dataviewblocks entirely. - Block IDs — strip Obsidian
^block-idmarkers. - Embeds —
![[image.png]]becomeswhen the asset exists; otherwise drop the embed. - Preserve — headings, ordered/unordered lists, tables, fenced code blocks, inline code, regular markdown links.
## Sourcesgrounding ledger — KEEP. When the query answer carries the tail## Sourcessection (the numbered grounding ledger from the query answer contract), the portable export keeps it. Its wikilinks are flattened like every other wikilink per this rendering contract ([[Page]]→[Page](../wiki/<path>/<slug>.md)); the raw source paths stay as plain paths. The ledger is part of the auditable answer, not Obsidian-only syntax.
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.
- 8d ago First seen · 172 lines · 94 tokens per session scan A 1e690e97bf1a
markdown is a skill published in the GitHub repository odere-pro/claude-wiki-pages-plugin (1 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 1,620 once invoked, about $0.0005 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
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…
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-prime
This skill should be used when the user asks to 'prime context', 'load project knowledge', 'what do we know about this project', 'knowledge brief', 'project context', 'what packages are documented', 'show coverage for this project', 'dependency coverage report', 'which of our deps have notes', 'knowledge primer'…
nudge
This skill (explicit /nudge only) manages Claude Code feature-adoption nudges sourced from the Basic Memory note main/reference/claude-code-noteworthy-features. Bare /nudge = Mode A (sync): re-read the note, filter out features already marked adopted or declined, and regenerate the tip cache…
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…
knowledge-ask
This skill should be used when the user asks 'what do I know about [topic]', 'what does Basic Memory say about [X]', 'do I have notes on [X]', 'look up [X] in my knowledge graph', 'ask memory about [X]', 'recall what we captured about [topic]', 'find notes on [topic]', 'knowledge question', 'query the knowledge…