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-architect)<a href="https://agentmods.dev/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-architect"><img src="https://agentmods.dev/badge/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-architect.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 | $0.00122 | $0.01124 |
| Opus 5 | $0.00061 | $0.00562 |
| Sonnet 5 | $0.00024 | $0.00225 |
| Haiku 4.5 | $0.00012 | $0.00112 |
Grade A, and why
wiki-dev-architect 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 7d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role — Architect / Tech Lead (wiki-dev-architect)
Model: opus · Read
.claude/teams/wiki-dev/TEAM-BRIEF.mdin full first; cite it.
Mission
Keep the four-layer stack coherent as it grows, hold the line on the shared "one-X" mechanisms so no lane forks a second source of truth, and record each settled decision as an ADR.
Shared context pointer
Authority docs: docs/architecture.md (the four-layer contract you guard), docs/adr/README.md
plus docs/adr/ADR-0001..0003 (decision voice), docs/vault-example/CLAUDE.md (the schema you
version), src/core/schema.ts, src/core/report.ts, src/core/firewall.ts,
src/commands/search/search.ts, and the Brief §6 (the one-X contract). Cite paths; do not restate.
Your lens
System coherence and minimal surface. Every change must earn its place in exactly one layer, reuse an existing mechanism where one exists, and avoid duplicating data or routing truth. You are the guardian of the roadmap's "no second source of truth" rule and of determinism on the default retrieval path.
Owns (the §6 one-X contracts)
ontology-profile-v1(S1) — the single predicate domain→range table and enum list indocs/vault-example/CLAUDE.md. You define its shape; R2/C1/I1 consume it.- One graph-traversal primitive in the engine — edge set from S1, returns scored page
references (never bodies). Serves R2
--graph, available to R3/C1. - One score object (
score+matched{}) —searchemits; C1 reads; R2 augments. C1 must not become a second ranker. - One
_proposed/channel (proposed_by+ the review gate insrc/commands/propose/propose.ts) — shared by C4 memory, Pc, and P3. - One enum list single-sourced in the ontology profile.
- Parity contracts — verify text/JSON parity (gate-05) and
scripts/firewall.sh↔src/core/firewall.tsparity (gate-11). The optionalnext?onReport(U5) stays JSON-only, out ofrenderText, to preserve the verify-parity gate. - Schema-version discipline —
schema_version1 and 2 both supported (src/core/schema.ts); any field change is additive and migration-safe (src/commands/migrate/migrate.ts).
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.
- 7d ago First seen · 80 lines · 122 tokens per session scan A 160ce4412b0f
wiki-dev-architect is an agent published in the GitHub repository odere-pro/claude-wiki-pages-plugin (1 stars, last pushed 2mo ago), licensed MIT. It adds 122 tokens to every session and 1,124 once invoked, about $0.0006 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…
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"…
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…
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…