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.
npx skills add dr-robert-li/cowork-wordpress-expert --skill diagnostic-arch-narrativegit clone --depth 1 https://github.com/dr-robert-li/cowork-wordpress-expertWrote 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/skills/dr-robert-li/cowork-wordpress-expert/diagnostic-arch-narrative)<a href="https://agentmods.dev/skills/dr-robert-li/cowork-wordpress-expert/diagnostic-arch-narrative"><img src="https://agentmods.dev/badge/skills/dr-robert-li/cowork-wordpress-expert/diagnostic-arch-narrative/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/skills/dr-robert-li/cowork-wordpress-expert/diagnostic-arch-narrative"><img src="https://agentmods.dev/badge/skills/dr-robert-li/cowork-wordpress-expert/diagnostic-arch-narrative.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 | $0.00082 | $0.03545 |
| Opus 5 | $0.00041 | $0.01773 |
| Sonnet 5 | $0.00016 | $0.00709 |
| Haiku 4.5 | $0.00008 | $0.00354 |
Grade A, and why
diagnostic-arch-narrative scanned grade A with 1 finding 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 11d 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
"detail": "## Overall Health: Grade C\n\nScan covered 4 domains with 11 findings total (1 critical, 4 warning, 6 informational).\nFirst scan for this site — no prior data available for trend comparison.\n\n### Security\n Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnostic: Architecture Narrative Synthesizer
CRITICAL SEQUENCING REQUIREMENT: This skill MUST run LAST in the /diagnose full-mode skill list. If it runs before other skills complete, COMBINED_FINDINGS will be incomplete and the narrative will be misleading. Register it at the end of the skill execution array.
You synthesize findings from all diagnostic skills in the current run into a single cross-domain health narrative. You do NOT run any new checks, connect to WordPress, execute WP-CLI commands, or grep files. You read structured findings and produce a single ARCH-NARR finding with an A-F health grade, domain-grouped bullet-point narrative, and "Top 3 issues to fix first" ranked list.
Overview
Individual diagnostic skills (security, code quality, database health, performance, architecture) each produce focused technical findings in their domain. After all skills complete, COMBINED_FINDINGS contains the full picture — but users need a synthesized cross-domain view that tells them:
- What grade is their site at overall?
- What are the key issues per domain — in one place?
- What three things should they fix first?
This skill is the culminating output of a full diagnostic run. It is an aggregator, not a probe.
What this skill does NOT do:
- Connect to the WordPress site via SSH, Docker, or direct access
- Run WP-CLI commands (no
wpcommands) - Execute grep or find on the codebase
- Generate new findings through code analysis
- Run any bash commands except reading the prior report file
What this skill DOES do:
- Read COMBINED_FINDINGS (JSON array passed by /diagnose)
- Optionally read memory/{site}/latest.md for prior scan grade comparison
- Apply the grading matrix (identical to report-generator thresholds)
- Group findings by domain category
- Rank top 3 priority issues
- Produce exactly ONE structured finding: ARCH-NARR
Input Sources
Source 1: COMBINED_FINDINGS (Required)
The primary input is the COMBINED_FINDINGS JSON array assembled by /diagnose after all preceding skills complete. This array contains every finding from every skill that ran in the current session.
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.
- 11d ago First seen · 306 lines · 82 tokens per session scan A 6f09dfcecd6d
diagnostic-arch-narrative is a skill published in the GitHub repository dr-robert-li/cowork-wordpress-expert (28 stars, last pushed 6mo ago), licensed MIT. It adds 82 tokens to every session and 3,545 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…