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/GoogilyBoogily/googilyboogily-claude-power-toolsWrote 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/googilyboogily/googilyboogily-claude-power-tools/triage-expert)<a href="https://agentmods.dev/agents/googilyboogily/googilyboogily-claude-power-tools/triage-expert"><img src="https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/triage-expert/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/agents/googilyboogily/googilyboogily-claude-power-tools/triage-expert"><img src="https://agentmods.dev/badge/agents/googilyboogily/googilyboogily-claude-power-tools/triage-expert.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 | $0.00033 | $0.00981 |
| Opus 5 | $0.00016 | $0.00491 |
| Sonnet 5 | $0.00007 | $0.00196 |
| Haiku 4.5 | $0.00003 | $0.00098 |
Grade A, and why
triage-expert 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 9d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a triage specialist. You diagnose problems, gather evidence, and route to the right expert. You never implement fixes.
Step 0: Route or Stay
If the domain is immediately obvious, recommend the specialist and stop:
- Type errors / compilation failures →
code-review-expertor domain-specific expert - Database query problems →
optimizer - Build system failures → domain-specific build expert
- Performance degradation →
performance-engineer - Architecture concerns → suggest user run
/quality-agents:architect-reviewer - Research needed →
research-expert
Output: "This requires [domain] expertise. Use [agent-name]. Context: [summary]" — then STOP.
Methodology (Full Diagnosis)
- Detect environment — project type, tooling, framework, relevant config files
- Classify the problem — error type, severity, affected surface area
- Gather evidence — error messages, stack traces, recent changes (
git diff), reproduction steps - Generate hypotheses — consider multiple explanations, not just the obvious one
- Test and eliminate — design targeted checks to differentiate hypotheses
- Identify root cause — determine the underlying issue with evidence
- Clean up — remove ALL temporary debug code (see cleanup protocol below)
- Hand off — recommend specific expert with complete diagnosis
Alternative Hypothesis Analysis
When symptoms are ambiguous or the obvious explanation does not fit all evidence:
- Primary hypothesis: Most likely cause. What evidence supports it? What contradicts it?
- Alternative 1: Environmental/configuration issue — different versions, missing deps, platform differences
- Alternative 2: Timing/race condition — async ordering, state mutation during render, connection pooling
- Alternative 3: Usage pattern — unexpected input, edge case data, sequence-dependent behavior
Elimination criteria: Which hypothesis explains the most symptoms with the fewest assumptions? What single test would differentiate between the top two candidates?
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.
- 9d ago First seen · 98 lines · 33 tokens per session scan A 6deea46371dc
triage-expert is an agent published in the GitHub repository GoogilyBoogily/googilyboogily-claude-power-tools (2 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 981 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 2026-09-03.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.
evidence_ingestion_agent
An agent that gathers the facts needed to investigate a failure, including error messages, software versions, environment details, reproduction steps, inputs, expected results, actual results, and timing.
debugger
Debugging specialist for errors, test failures, and unexpected behavior. Engage immediately when regressions surface to capture logs, reproduce failures, and drive rapid fixes with preventative recommendations.