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.
git clone --depth 1 https://github.com/odere-pro/claude-wiki-pages-pluginWrote 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/commands/odere-pro/claude-wiki-pages-plugin/wiki)<a href="https://agentmods.dev/commands/odere-pro/claude-wiki-pages-plugin/wiki"><img src="https://agentmods.dev/badge/commands/odere-pro/claude-wiki-pages-plugin/wiki.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 | $0.00027 | $0.00576 |
| Opus 5 | $0.00014 | $0.00288 |
| Sonnet 5 | $0.00005 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00058 |
Grade A, and why
wiki 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 6d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/claude-wiki-pages:wiki
Top-level entry point for claude-wiki-pages. One verb the user types; the plugin figures out the rest.
What this command does
- Probe vault state. Resolve the vault path via
scripts/resolve-vault.sh. Inspectvault/CLAUDE.md(doesschema_versionexist?),vault/raw/(any files newer than the last entry invault/wiki/log.md?), and the most recentwiki/log.mdoperation (was the previous run aningestnot yet followed by alint?). - Delegate to the orchestrator. Dispatch the user's prompt and the probe results to the
claude-wiki-pages-orchestrator-agentvia theTasktool. The orchestrator owns the routing decision; this command does not. - Surface the result. Print whatever the orchestrator returns. Specialist fan-out is invisible to the user.
When to use this command
- The user just installed the plugin and wants to start.
- New files dropped into
vault/raw/. - A vault that has not been touched in a while needs to catch up.
- A natural-language question against the wiki.
- Any time the user is unsure which
llm-wiki-*skill or agent to invoke — this command picks for them.
For power users running a single phase directly, the existing llm-wiki-* skills and agents remain available and unchanged.
Invocation
Pass the user's prompt verbatim ($ARGUMENTS) to the orchestrator. Do not pre-classify the prompt; that is the orchestrator's job. If $ARGUMENTS is empty, hand control to the orchestrator anyway — it will probe state and either run the wizard, run an ingest, or ask one clarifying question.
Task → claude-wiki-pages-orchestrator-agent
prompt: $ARGUMENTS
context: vault path, schema version (if present), raw/ count, last wiki/log.md entry
Companion command
/claude-wiki-pages:doctor— environment health check. Run it once after install and any time something feels wrong.
Specification anchor
Contracts: docs/architecture.md (orchestrator command & claude-wiki-pages-orchestrator-agent contract).
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.
- 6d ago First seen · 44 lines · 27 tokens per session scan A f4ba3cf016e9
wiki is a command published in the GitHub repository odere-pro/claude-wiki-pages-plugin (1 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 576 once invoked, about $0.0001 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 commands, from other repositories
resume
Resume a previous session. Reads recent session logs, open tasks, and last decisions — gives Claude full context without re-explaining the project.
learn
Manually run the continuous-learner. Extract patterns from this session and write to .greatcto/lessons.md. Use when SessionEnd hook missed something or you want to capture a lesson mid-session.
recall
Search what this project knows about a concept — session history, and the documents written about it. Usage: /recall.
ccr
CCR (Compressed Context with Retrieval) — recall the full original of context that greatcto compressed/filtered out, by its short id. The retrieval half of the compression layer.
rust-teach
One-time setup that scans your Rust project, understands its patterns and conventions, and writes a Rust-specific context section to your CLAUDE.md. Run once per project to establish persistent Rust guidelines.
learn
Codify implicit codebase knowledge as agent rules.