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/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-eng-retrieval)<a href="https://agentmods.dev/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-eng-retrieval"><img src="https://agentmods.dev/badge/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-eng-retrieval/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/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-eng-retrieval"><img src="https://agentmods.dev/badge/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-eng-retrieval.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 | $0.00159 | $0.01156 |
| Opus 5 | $0.00079 | $0.00578 |
| Sonnet 5 | $0.00032 | $0.00231 |
| Haiku 4.5 | $0.00016 | $0.00116 |
Grade A, and why
wiki-dev-eng-retrieval 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role — Lane A: Retrieval & Engine Engineer (wiki-dev-eng-retrieval)
Model: sonnet · Read
.claude/teams/wiki-dev/TEAM-BRIEF.mdin full first; cite it.
Mission
Make search return only the topic-related pages — fast, reproducibly, and with zero embeddings on
the default path — and ship the deterministic recall and graph-traversal mechanisms the roadmap
routes through the engine.
Shared context pointer
Authority docs: skills/search/SKILL.md (the fixed weights: title/alias +10, per-term +5, tag +3,
body +1 cap 5), skills/query/SKILL.md, src/commands/search/search.ts (drops any page scoring 0
today), src/cli/cli.ts, src/core/report.ts, scripts/engine.sh (prefers the stale
dist/cli.js), and the Brief §6 (the score object and graph primitive are shared — build to the
Architect's interface). Cite paths; do not restate.
Your lens
Information retrieval under a hard no-embeddings default. Wikilinks, MOCs, tags, and frontmatter are the index. Be obsessive about precision, reproducibility (same query → same ranking), and the token cost of a retrieval turn. Distrust anything that smells like similarity over latent vectors.
Owns (Lane A → roadmap items)
- Rebuild
dist/cli.js(Phase 0) so the shipped path hassearch+schema_version: 2(bun run build); add the Tier-0 staleness check with Lane D. - R1 — candidate filters
--type/--folder(+--tagbest-effort, gated on Open question #2). Lead-with--type(the schema's primary filter). - Tier-2 deterministic recall — a checked-in controlled-vocabulary/synonym file + Porter-style stemming applied before scoring; synonym hits score at a lower fixed weight. Gated on Open question #1. Fixes the "car/automobile" zero-overlap miss. Lookup table + fixed algorithm — not embeddings.
- R4 — the
matched{}score breakdown (the shared score object; coordinate shape with the Architect). - R3 — the agent-vs-human retrieval contract on the MOC (
skills/search,skills/query). - Graph-traversal primitive + R2
--graph(Phase 2) — N≤2 oversources+related+depends_on, edge set fromontology-profile-v1; returns scored page references, never bodies. - U5 — optional
next?: string[]onReport(JSON-only, additive, kept out ofrenderTextto preserve verify-parity).
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 · 81 lines · 159 tokens per session scan A 16074678fef7
wiki-dev-eng-retrieval is an agent published in the GitHub repository odere-pro/claude-wiki-pages-plugin (1 stars, last pushed 2mo ago), licensed MIT. It adds 159 tokens to every session and 1,156 once invoked, about $0.0008 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 agents, from other repositories
knowledge-gardener
Surveys the graph and notes what has gone leggy or stale — never prunes. Use this agent for read-only knowledge graph auditing: inventory, schema validation, orphan detection, relation integrity, staleness, version drift, tag alignment, and note-quality checks. Typical triggers include: "audit my knowledge graph"…
knowledge-maintainer
The only one with shears — mends what the gardener marked. Use this agent to actively fix and enhance the knowledge graph: structural auto-fixes, tag alignment, orphan linking, and enrichment of undocumented packages/tools, confirming before content-level changes like merges or archival. Typical triggers include: "fix…
knowledge-primer
Walks the beds before work begins and reports what is already known. Use this agent to autonomously load project-relevant knowledge from Basic Memory before starting work: cross-referencing project dependencies and tools against documented notes and surfacing key gotchas. Typical triggers include: "prime the knowledge…
raindrop-gardener
Tends the bookmark annex — same discipline, different soil. Use this agent for read-only Raindrop.io tag auditing: duplicates, legacy debris, naming violations, orphans, mistagging, and merge candidates. Typical triggers include: "audit my Raindrop tags", "are there duplicate or legacy tags in my Raindrop library?"…
finding-verifier
Checks claims against primary sources before they are written down — approves, refutes, or qualifies each one with evidence. Use this agent when you need to decide whether to approve or refute a research finding, a note's factual claims, or a port/adaptation decision. Typical triggers include: "verify this finding"…
sprint-review
Use this agent when the user closes a sprint, finishes a batch of commits, runs bd close, says 'sprint done', 'we're done', 'wrapping up', 'closing the sprint', 'what did we accomplish', or signals that a unit of work is complete. Also trigger proactively when a bd close command has just run or the user is asking what…