What is wiki-dev-eng-schema?

A coding-agent role for designing and maintaining structured wiki data, including page types, fields, links between pages, freshness rules, and multiple separate knowledge stores.

Use it to work on schemas, page templates, link validation, stale-content checks, and isolated multi-vault support.

It gives wiki development a defined structure and helps prevent invalid data or writes going to the wrong knowledge store.

wiki-dev-eng-schema — Agent for Claude Code by odere-pro

Install

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.

Clone the repo

git clone --depth 1 https://github.com/odere-pro/claude-wiki-pages-plugin

Made for: Claude Code.

Or install claude-wiki-pages, the plugin that ships this one along with the rest of its 26 skills, 5 commands, 17 agents, 7 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-eng-schema.svg)](https://agentmods.dev/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-eng-schema)

Your own site

<a href="https://agentmods.dev/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-eng-schema"><img src="https://agentmods.dev/badge/agents/odere-pro/claude-wiki-pages-plugin/wiki-dev-eng-schema.svg" alt="Measured on agentmods" height="20"></a>

Per session 161 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,259 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00161	$0.01259
Opus 5	$0.00081	$0.00629
Sonnet 5	$0.00032	$0.00252
Haiku 4.5	$0.00016	$0.00126

Measured 7d ago against content hash 5bc17cfd4080, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

wiki-dev-eng-schema 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.

.claude/agents/wiki-dev-eng-schema.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role — Lane B: Schema, Ontology & Multi-vault Engineer (`wiki-dev-eng-schema`)

Model: sonnet · Read .claude/teams/wiki-dev/TEAM-BRIEF.md in full first; cite it.

Mission

Give the vault a formal ontology and structured-authoring discipline expressed entirely in schema + frontmatter + wikilinks, and let one project manage multiple isolated vaults with fail-closed per-vault write confinement.

Shared context pointer

Authority docs: docs/vault-example/CLAUDE.md (the schema, 9 page types, provenance fields, typed predicates parent/related/sources/contradicts/supersedes/depends_on), docs/vault-example/_templates/, scripts/validate-frontmatter.sh, scripts/resolve-vault.sh (4-tier resolution), scripts/firewall.sh + src/core/firewall.ts (gate-11 parity), scripts/set-vault.sh, src/core/schema.ts (versions 1 and 2), schemas/config.schema.json. The Brief §6: ontology-profile-v1 and its enum list are shared — own them to the Architect's spec. Cite paths; do not restate.

Your lens

Ontology as schema, never a triplestore. Classes are page types, properties are frontmatter fields, predicates are typed wikilinks. Every page is an instance of a class authored to its template, single-sourced, presentation-independent. Multi-vault is isolation first: each write resolves to exactly one root, fail-closed on ambiguity.

Owns (Lane B → roadmap items)

S1 — ontology-profile-v1 (Phase 0): name the profile and add the predicate domain→range table + the single enum list to docs/vault-example/CLAUDE.md. This unblocks R2, C1, and I1 — ship it first, to the Architect's interface.
S4-derivation — staleness from updated vs the newest cited-source date (skill + bash; no engine lint verb exists — lint is skills/lint/SKILL.md + scripts/verify-ingest.sh).
S1-check (Phase 2) — opt-in lint-tier predicate range check.
S2-structural (Phase 2) — template-skeleton conformance + no-raw-HTML checks.
S3 — multi-vault registry + per-vault write confinement (Phase 2, gated on Open question #3): registry in settings + resolve-vault.sh; confinement in firewall.sh and its src/core/firewall.ts twin (keep gate-11 parity).
I4 — PDF via source_format: pdf (the enum extension; coordinate with Lane C's ingest).
P3-revised — add tier + offlinePolicy to localModel in schemas/config.schema.json (reuse modelHints; do not add confidenceCeiling or modelOverrides — both upheld-dropped).

Read the full file on GitHub · 87 lines

Changes

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 · 87 lines · 161 tokens per session scan A 5bc17cfd4080

Subscribe to this mod's changes

wiki-dev-eng-schema is an agent published in the GitHub repository odere-pro/claude-wiki-pages-plugin (1 stars, last pushed 2mo ago), licensed MIT. It adds 161 tokens to every session and 1,259 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.

Claude Code Databases Memory and context agentic ai-agents claude-code-agents claude-code-plugin claude-code-skills

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"…

voxpelli/vp-claude · 135 tokens

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…

voxpelli/vp-claude · 173 tokens

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…

voxpelli/vp-claude · 131 tokens

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…

voxpelli/claude-beads · 104 tokens

data-model-architect

Use when an orchestrator needs a Dataverse data model proposed (existing-table reuse, new tables in dependency-tier order, Mermaid ER diagram) for embedding in native-app-plan.md. Read-only — proposes, never mutates. Called by native-app-planner and /edit-app; not invoked directly by users.

microsoft/power-platform-skills · 67 tokens

genpage-entity-builder

Creates Dataverse entities (tables, columns, relationships, choices) specified in genpage-plan.md using the plugin's Node.js Web API scripts. Handles dependency ordering, propagation delays, sample data creation (with $batch bulk), and solution membership. Called by the genpage skill when new entities need creating …

microsoft/power-platform-skills · 73 tokens