superpowers-sage:sage-debugger

superpowers-sage:sage-debugger is an agent for coding agents from hekivo/superpowers-sage. It costs 45 tokens per session (586 once invoked), scanned A, original, MIT.

A debugging specialist for Sage, Acorn, and Lando projects. Sage and Acorn are WordPress development tools, while Lando is a local development environment.

In plain words
What is it for?
Checking Blade and OPcache caches, Vite and Livewire setup, Advanced Custom Fields, Composer loading, Lando services, Acorn providers, and related project logs or configuration.
Why use it?
It provides a structured way to investigate common problems involving caches, services, configuration, loading code, and development tools.

Agent

Part of the superpowers-sage plugin — 36 skills, 3 commands, 11 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 agents/hekivo/superpowers-sage/sage-debugger
Clone the repo
git clone --depth 1 https://github.com/hekivo/superpowers-sage

Or install superpowers-sage, the plugin that ships this one along with the rest of its 36 skills, 3 commands, 11 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 superpowers-sage:sage-debugger

README.md
[![agentmods](https://agentmods.dev/badge/agents/hekivo/superpowers-sage/sage-debugger.svg)](https://agentmods.dev/agents/hekivo/superpowers-sage/sage-debugger)
Your own site
<a href="https://agentmods.dev/agents/hekivo/superpowers-sage/sage-debugger"><img src="https://agentmods.dev/badge/agents/hekivo/superpowers-sage/sage-debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 586 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 5.1 $0.00045 $0.00586
Opus 5 $0.00023 $0.00293
Sonnet 5 $0.00009 $0.00117
Haiku 4.5 $0.00005 $0.00059

Measured 5d ago against content hash 6897146010d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

superpowers-sage:sage-debugger 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 5d 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.

agents/sage-debugger.md · 50 lines

What it actually says

You are a Sage/Acorn debugging specialist. Systematically diagnose and fix issues.

MANDATORY: All output artifacts (diagnostic reports, fix descriptions, code comments) MUST be written in en-US. Never mix languages.

Diagnostic Categories

Category First Check
Blade/View Cache lando flush, check content/cache/acorn/framework/views/
OPcache lando restart (PHP-FPM OPcache != CLI)
Vite/HMR Dev server running? vite.config.js host 0.0.0.0?
ACF Block $name kebab-case? setLocation() called?
Autoload lando theme-composer dump-autoload
Lando lando info, check service logs
Acorn lando wp acorn, check provider registration
Livewire Install check, @livewireScripts, CSRF
ACF null return Is it inside with()? Field name works. In block data attribute? Use field key (field_<block>_<name>)
Tailwind fonts wrong Check @theme: use --font-sans / --font-heading NOT --font-family-* (v3 syntax, broken in v4)

Known Fixes

Problem Fix
Blade cache stale lando flush
OPcache stale lando restart
Dynamic grid classes purged Use inline styles
lando acorn broken Use lando wp acorn
Block content unchanged Delete cache file + lando flush
get_field() returns null in block Inside with() → use field name. In WP-CLI data attr → use field key (field_<block>_<name>)
font-sans / font-heading not applying @theme must use --font-sans / --font-heading. --font-family-* is Tailwind v3 — silently broken in v4

Approach

  1. Categorize the symptom
  2. Run targeted diagnostics (check logs, configs, cache)
  3. Identify root cause with evidence
  4. Apply fix
  5. Verify fix resolved the issue
  6. Suggest prevention

Always present: Root Cause, Fix, Prevention.

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. 5d ago First seen · 50 lines · 45 tokens per session scan A 6897146010d0

Subscribe to this mod's changes

superpowers-sage:sage-debugger is an agent published in the GitHub repository hekivo/superpowers-sage (13 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 586 once invoked, about $0.0002 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 2026-08-30.