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/LeanAndMean/scramjetWrote 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/leanandmean/scramjet/scramjet-troubleshoot)<a href="https://agentmods.dev/commands/leanandmean/scramjet/scramjet-troubleshoot"><img src="https://agentmods.dev/badge/commands/leanandmean/scramjet/scramjet-troubleshoot/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/commands/leanandmean/scramjet/scramjet-troubleshoot"><img src="https://agentmods.dev/badge/commands/leanandmean/scramjet/scramjet-troubleshoot.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 | $0.00009 | $0.01109 |
| Opus 5 | $0.00005 | $0.00554 |
| Sonnet 5 | $0.00002 | $0.00222 |
| Haiku 4.5 | $0.00001 | $0.00111 |
Grade A, and why
scramjet:troubleshoot 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 4d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Troubleshoot
Goals
- Give the user a concise, evidence-grounded explanation of the gap between their intent and the observed Scramjet behavior.
- Identify the simplest supported root cause, distinguish observations from inference, and state material uncertainty plainly.
- Recommend only safe, concrete next steps.
Use the user's description, the current conversation, command instructions, tool results, logs, source, and external state as read-only evidence. Establish both the user's intent and the specific unexpected behavior before drawing a conclusion. If either remains materially ambiguous, ask the user instead of inventing it.
Do not edit command or source files, publish a GitHub issue, retry a side effect, or otherwise mutate state while diagnosing. Tool scoping is advisory, so these prohibitions apply even if another tool happens to be available.
Perform the following as internal lenses. Integrate relevant conclusions into the five-section answer; do not render these as additional reports:
- agent interpretation — Did the agent misunderstand, omit, or over-literalize an instruction?
- command instructions — Were the command's wording, ordering, constraints, or declared route incomplete or conflicting?
- harness and tool design — Did confusing names, descriptions, responses, errors, overlapping tools, missing capabilities, or lifecycle behavior contribute?
- user input — Was a user message ambiguous, misleading, factually incorrect, or reasonably interpreted another way?
- historical recurrence — Is this an isolated outcome or a pattern supported by relevant prior examples?
- user experience — Does the command name set the right expectation, is the behavior usable, and did invoking it provide value from the user's perspective?
Prefer the simplest root cause supported by evidence. Distinguish direct observations from inferences, identify contributing factors only when they changed the outcome, and verify current source or external state before relying on historical claims.
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.
- 4d ago Changed · +4 lines 02c379148b4b
- 9d ago First seen · 83 lines · 9 tokens per session scan A 2f0f7ca5a3ad
scramjet:troubleshoot is a command published in the GitHub repository LeanAndMean/scramjet (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 9 tokens to every session and 1,109 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
computer
Drive a computer's screen, mouse, and keyboard.
afr
Review feature - code review with fixes by a different agent (shortcut for feature-code-review).
fix
⚡⚡ Analyze and fix small issues [AUTO DETECT COMPLEXITY].
review
You are a helpful coding expert. You MUST provide a detailed, clear, organized and relevant review of the current codebase. If a user direction is provided, you MUST focus the scope of your review to that.
troubleshoot-setup
Command "troubleshoot-setup" from TechNickAI/claude_telemetry, covering setting up /troubleshoot command, quick start, 1. configure mcp server, 2. symlink for cursor compatibility and 3. connect error monitoring service.
checklist
Generate a custom checklist for the current feature based on user requirements.