engine-api

engine-api is a skill for Claude Code, Codex from odere-pro/claude-wiki-pages-plugin. It costs 134 tokens per session (3,640 once invoked), scanned A, original, MIT.

A documented command-line interface for managing a Claude wiki: a collection of linked notes with structured metadata.

In plain words
What is it for?
Use it to verify, repair, migrate, search, inspect, and configure wiki pages and their links.
Why use it?
It gives coding agents exact checks and machine-readable results instead of relying on manual inspection of notes and links.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the claude-wiki-pages plugin — 26 skills, 5 commands, 17 agents, 7 hooks shipped together

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.

agentmods
npx agentmods add skills/odere-pro/claude-wiki-pages-plugin/engine-api
Any agent
npx skills add odere-pro/claude-wiki-pages-plugin --skill engine-api
Clone the repo
git clone --depth 1 https://github.com/odere-pro/claude-wiki-pages-plugin

Made for: Claude Code, Codex.

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.

agentmods badge for engine-api

README.md
[![agentmods](https://agentmods.dev/badge/skills/odere-pro/claude-wiki-pages-plugin/engine-api.svg)](https://agentmods.dev/skills/odere-pro/claude-wiki-pages-plugin/engine-api)
Your own site
<a href="https://agentmods.dev/skills/odere-pro/claude-wiki-pages-plugin/engine-api"><img src="https://agentmods.dev/badge/skills/odere-pro/claude-wiki-pages-plugin/engine-api.svg" alt="Measured on agentmods" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,640 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00134 $0.03640
Opus 5 $0.00067 $0.01820
Sonnet 5 $0.00027 $0.00728
Haiku 4.5 $0.00013 $0.00364

Measured 4d ago against content hash 48c584b9f1ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

engine-api 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 4d 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.

skills/engine-api/SKILL.md · 343 lines

How it starts

The opening of the file, as written. The whole thing — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Engine API — the deterministic tool surface

The engine is a Bun CLI invoked through scripts/engine.sh <command> [--target <vault>] [--json]. It is the source of truth for anything that must be exact (the wikilink graph, frontmatter, MOC integrity). Agents call it and reason over its structured output instead of eyeballing the vault. Always pass --json for machine use.

Invocation

bash "${CLAUDE_PLUGIN_ROOT}/scripts/engine.sh" <command> --target <vault> --json

Global flags:

  • --target <vault> — the vault root to operate on. Always supply this when a vault registry is configured; omitting it lets the engine resolve the vault independently, which may disagree with the hook's resolved path.
  • --other-vaults <colon-separated-paths> — the registered vault roots other than the active one, used by the firewall command to enforce the cross-vault deny rule. Derive this value from registry_other_vaults in scripts/resolve-vault.sh rather than hard-coding paths. See Multi-vault operating rules for the full confinement contract (ADR-0009 + ADR-0016).
  • --json — emit structured JSON output. Always pass this for machine use.

If Bun is missing, the bridge prints a warning and exits 0 — degrade to the bash verifiers (verify-ingest.sh) rather than failing.

Commands

verify — read-only integrity check

Ports verify-ingest.sh CHECK 0–3. Returns a report; exit 1 when any error, else 0.

{
  "command": "verify",
  "vault": "docs/vault",
  "findings": [
    {
      "severity": "error|warn|info",
      "check": "schema|index-duplicates|sources-format|moc|orphan-sources|topic-folder|legacy-index-filename",
      "message": "…",
      "file": "…"
    }
  ],
  "errors": 0,
  "warnings": 0,
  "clean": true
}

At schema_version 3 the per-folder index is a folder note (wiki/<topic>/<topic>.md, type: index). A legacy _index.md is still accepted, but verify emits a WARN-severity legacy-index-filename finding for it — message: run engine.sh migrate --write. The WARN never flips clean to false on its own.

Read the full file on GitHub · 343 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.

  1. 4d ago First seen · 343 lines · 134 tokens per session scan A 48c584b9f1ac

Subscribe to this mod's changes

engine-api is a skill published in the GitHub repository odere-pro/claude-wiki-pages-plugin (1 stars, last pushed 2mo ago), licensed MIT. It adds 134 tokens to every session and 3,640 once invoked, about $0.0007 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.