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/claude)<a href="https://agentmods.dev/commands/odere-pro/claude-wiki-pages-plugin/claude"><img src="https://agentmods.dev/badge/commands/odere-pro/claude-wiki-pages-plugin/claude.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 | $0.00000 | $0.00699 |
| Opus 5 | $0.00000 | $0.00349 |
| Sonnet 5 | $0.00000 | $0.00140 |
| Haiku 4.5 | $0.00000 | $0.00070 |
Grade A, and why
CLAUDE 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 8d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
commands — the engine verbs
Each subdirectory is one engine verb dispatched by
../cli/cli.ts: <cmd>/<cmd>.ts exports a pure handler that
resolves the vault, does its work through ../core/
primitives, and returns its own typed report. Commands stay thin — they compose
core checks and builders; they do not reimplement them. The canonical output
schema is the shared Report / Finding model in
../core/report.ts; verify returns it directly, and the
other commands return a command-specific report type rendered uniformly by the
router. Run a verb as claude-wiki-pages <cmd>; add --json for the structured
form an agent consumes. Each <cmd>/ carries its own CLAUDE.md with the local
contract.
The implemented commands
| Command | Purpose | Report type |
|---|---|---|
verify |
Deterministic vault integrity check (CHECK 0–5). | Report |
fix |
Idempotent repair of safe structural drift. | FixReport |
heal |
Git-bounded verify → fix → re-verify self-heal loop. |
HealReport |
doctor |
Environment + vault health check (D01–D12). | DoctorReport |
config |
Show or validate the effective layered config. | ConfigReport |
migrate |
Upgrade a vault's schema_version (additive, git-bounded). |
MigrateReport |
search |
Deterministic full-text + frontmatter search over wiki/. |
SearchReport |
firewall |
Decide whether a write to --file is permitted. |
FirewallReport |
backlog |
Probe outstanding maintenance (pending raw, days since lint). | BacklogReport |
propose |
Review / approve / reject drafted pages in _proposed/. |
ProposeReport |
route |
Degraded-mode routing decision: Claude / local / blocked (ADR-0018). | RouteReport |
snapshot |
Git-bound an LLM write phase (pre checkpoint / post commit). |
SnapshotReport |
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.
- 8d ago First seen · 43 lines · 0 tokens per session scan A 9577331cf712
CLAUDE is a command published in the GitHub repository odere-pro/claude-wiki-pages-plugin (1 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 699 tokens. 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
psql-query
Run ad-hoc PostgreSQL analytics queries against dev/test database.
discover
Run a full product discovery cycle — from outcome definition through opportunity mapping, prioritisation, and experiment design. Use when the team isn't sure what to build next, or before writing a PRD for a complex feature space.
coding-audit
Medical-coding / revenue-cycle compliance audit. Invokes rcm-reviewer to assess autonomous ICD-10-CM / CPT / HCPCS coding for False Claims Act exposure (upcoding/unbundling), NCCI edits + MUEs, medical necessity (LCD/NCD), modifier discipline, HIPAA minimum-necessary — and force a certified-coder (CPC/CCS) sign-off.
tax-review
Tax-filing compliance check — invokes tax-reviewer to produce TM-tax-{slug}.md with MeF e-file schema, Form 8879, PTIN/Circular 230, and IRC §7216 consent gaps.
esp-teach
One-time project setup -- discover hardware, find datasheets, persist context to CLAUDE.md.
swift-critique
Critique SwiftUI code for patterns, design, clean code, accessibility, and performance.