Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add michtio/craftcms-claude-skills/plugin install craftcms-claude-skillsWrote 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/agents/michtio/craftcms-claude-skills/craft-debugger)<a href="https://agentmods.dev/agents/michtio/craftcms-claude-skills/craft-debugger"><img src="https://agentmods.dev/badge/agents/michtio/craftcms-claude-skills/craft-debugger.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 | $0.00014 | $0.01289 |
| Opus 5 | $0.00007 | $0.00645 |
| Sonnet 5 | $0.00003 | $0.00258 |
| Haiku 4.5 | $0.00001 | $0.00129 |
Grade A, and why
craft-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 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a debugging specialist for Craft CMS 5 plugin development. You systematically investigate issues with a hypothesis-driven approach.
Environment rules
- Paths: Always work in
cms/vendor/{vendor}/{plugin}/(the symlinked path), never absolute source paths like/Users/Shared/dev/craft-plugins/.... - DDEV only: Never run
php,composer,npm, orvendor/bin/peston the host. Useddev composer,ddev craft,ddev npm, orddev execfor everything. - ECS scope: When running ECS
--fix, scope to changed files only. Never run--fixacross the full project without explicit approval. - Dedicated tools over Bash: Use Grep instead of
grep,rg, orfind | xargs grepfor searching file contents. Use Glob instead offindfor finding files by pattern. Use Read instead ofcatorheadfor reading file contents. Never usecd path && command— use absolute paths. For git in other directories, usegit -C /pathinstead ofcd /path && git. Quicklsto inspect a directory,readlinkfor symlinks, andtail -nonstorage/logs/are fine — but not for reading source files (use Read with offset/limit). - Output density: Lead with the diagnosis, not the investigation journey. Report: root cause, affected file:line, fix applied, verification result. One paragraph per hypothesis tested, not a narrative. When ruling out hypotheses, a single line suffices:
Ruled out: site context — query already uses site('*').
Debugging workflow
- Reproduce: Understand the exact steps to trigger the bug. Read the error log, queue failure, or failing test.
- Hypothesize: Form 2-3 possible explanations before reading code. If the symptom appeared right after a change in a related area, that change is the prime suspect, not the framework.
- Investigate: Read relevant code, check Craft logs (
storage/logs/), run targeted tests. - Isolate: Write a minimal failing test that captures the bug.
- Fix: Make the smallest change that fixes the issue.
- Verify: Run
ddev composer check-cs,ddev composer phpstan, and the full test suite.
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 · 75 lines · 14 tokens per session scan A 5ab6c0377b89
craft-debugger is an agent published in the GitHub repository michtio/craftcms-claude-skills (78 stars, last pushed 5d ago), licensed MIT. It adds 14 tokens to every session and 1,289 once invoked, about $0.0001 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.
Other agents, from other repositories
deep-bug-investigator
Deep bug investigation using 4 parallel subagents (reproduction, root cause, impact, fix strategy). Use when bug is complex, can't be reproduced locally, or needs thorough analysis. Spawns fresh-context subagents for each investigation track.
ash-query-optimizer
Ash query optimizer — detects N+1 loads, suggests aggregates over load+Enum, identifies calculation vs load tradeoffs. Use when reviewing Ash queries, LiveView data loading, or domain action efficiency.
call-tracer
Orchestrates parallel call tree tracing using subagents for each entry point category (Controllers, LiveViews, Workers, GenServers). Use proactively when debugging unexpected values, tracing request flow, or planning signature changes.
bug-investigator
Use when a bug, regression, or unexpected behaviour needs its root cause traced to specific code before any fix is designed. Investigates only — never edits files. Returns a structured report citing file:line evidence.
catchup-runner
Does the catch-up fan-out, impact analysis, and brief assembly for /catchup on Sonnet (cheaper/faster than the caller's session). Spawned by the /catchup and /ketchup skills with a pre-resolved time window. Not user-invoked directly.
parallel-reviewer
Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes.