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 wayne930242/straw-boss --skill troubleshooting-appgit clone --depth 1 https://github.com/wayne930242/straw-bossWrote 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/wayne930242/straw-boss/troubleshooting-app)<a href="https://agentmods.dev/skills/wayne930242/straw-boss/troubleshooting-app"><img src="https://agentmods.dev/badge/skills/wayne930242/straw-boss/troubleshooting-app/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/wayne930242/straw-boss/troubleshooting-app"><img src="https://agentmods.dev/badge/skills/wayne930242/straw-boss/troubleshooting-app.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 | $0.00048 | $0.00823 |
| Opus 5 | $0.00024 | $0.00411 |
| Sonnet 5 | $0.00010 | $0.00165 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
troubleshooting-app 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
See docs/roles.md for the cast of characters and the authority framework this skill operates under — not redefined here.
A reported failure is expected to end fixed, not merely explained. Diagnosis and repair stay in one shipping-task single-loop so the same agent preserves the evidence and context it discovers.
An integration preflight is useful only when both conditions hold: the failure crosses an integration boundary, and its explanatory conclusion is needed to shape or schedule later dispatches. It supplies evidence-backed coordination input. A symptom that one resolved app can diagnose and repair stays in the same worker.
The fix runs through shipping-task's git lifecycle and mode decision.
When the continuous loop locates the cause in data, configuration, infrastructure, or another app, its root-cause account and evidence supply the next route.
Task 1: Resolve the app
Invoke work-on now. Even for a live incident, you need the target app before digging in.
Verification: the target app is established before Task 2.
Task 2: App-code or infrastructure?
Classify from evidence the user already supplied. Symptoms such as environment-only failure, failure without an app change, or an unexplained server response can point to infrastructure.
- Clearly infrastructure: hand off to the project's infrastructure/ops owner with the supplied evidence.
- App-level or uncertain: continue to Task 3 so the target-app loop can distinguish an app cause from an external dependency.
Verification: the classification cites supplied evidence and uncertainty continues to the target-app loop.
Task 3: Choose the continuous or preflight branch
Use an integration preflight only when the supplied evidence already shows the integration boundary and the later routing decision it must enable. Run it through dispatching-work in the resolved app and require an explanatory, falsifiable root-cause account with evidence references to logs, tests, commands, files, or artifacts. Its reality anchor is an independent agent's adversarial review of the account.
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 · 58 lines · 48 tokens per session scan A 15c70eea0400
troubleshooting-app is a skill published in the GitHub repository wayne930242/straw-boss (3 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 823 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 2026-08-31.
Other skills, from other repositories
issue-analyze
GitHub Issue and PR review thread deep analysis with Codex blind verdict. Use when: analyzing issue root cause, classifying problems, investigation planning, triaging PR review comments for actionability. Not for: fixing bugs (use bug-fix), code exploration (use code-explore). Output: classified analysis + verdict…
debug
Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.
code-explore
Pure Claude code investigation. Use when: tracing execution paths, understanding architecture, diagnosing issues. Not for: dual-perspective review (use code-investigate), code review (use codex-code-review). Output: analysis report with findings.
code-investigate
Dual-perspective code investigation. Use when: deep code analysis needing both Claude and Codex perspectives. Not for: quick exploration (use code-explore), code review (use codex-code-review). Output: integrated findings from dual analysis.
bug-fix
Bug fix workflow. Use when: fixing bugs, resolving issues, regression fixes. Not for: new features (use feature-dev), understanding code (use code-explore). Output: fix + regression test + review gate.
git-investigate
Git history investigation. Use when: tracking code changes, finding where bugs were introduced, root cause analysis. Not for: code exploration (use code-explore), issue analysis (use issue-analyze). Output: history trace + root cause report.