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 mystilleef/spae-framework --skill troubleshootgit clone --depth 1 https://github.com/mystilleef/spae-frameworkWrote 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/mystilleef/spae-framework/troubleshoot)<a href="https://agentmods.dev/skills/mystilleef/spae-framework/troubleshoot"><img src="https://agentmods.dev/badge/skills/mystilleef/spae-framework/troubleshoot.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 | $0.00020 | $0.01242 |
| Opus 5 | $0.00010 | $0.00621 |
| Sonnet 5 | $0.00004 | $0.00248 |
| Haiku 4.5 | $0.00002 | $0.00124 |
Grade C, and why
troubleshoot scanned grade C with 1 finding 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 7d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- prettier-ignore-start --> How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Troubleshoot
When to use
- Invoke for failures, regressions, unclear errors, flaky behavior, broken tests, build issues, runtime faults, or unexpected output.
- Execute immediately upon invocation. Don't wait for confirmation.
Goal
- Observe real behavior, test one hypothesis at a time, fix proven root causes, and verify the result.
- Identify the root cause with evidence.
- Apply the smallest safe fix.
- Prove the fix through targeted tests and the strongest relevant check.
Input
Determine input by one of the following:
- Issue, symptom, error, failing command, stack trace, or test failure provided by the user.
- Current repository state and failing verification when the user gives only a broad troubleshooting request.
Testing
See references/testing-guide.md for test structure, isolation,
mocking, assertion, and performance standards.
Shell Commands
See references/shell-command-guide.md for command safety, timeouts,
redirects, and non-interactive environment directives.
Cleanup
See references/cleanup-guide.md for the self-introduced-artifact
checklist and diff-only audit scope.
Workflow
- GATE—Require an actionable symptom: error, failure, trace, or incorrect output. Halt and ask if none exists.
- ORIENT—Name the failure and scope in one sentence. State what won't change.
- PLAN—Read
references/shell-command-guide.md. State one likely root cause and one targeted check to confirm or reject it. - ACT—Execute:
- Reproduce the failure.
- Run the targeted check; on rejection, return to PLAN.
- After 3 rejections, trace data flow from entry point.
- Read
references/testing-guide.md. Write a failing test reproducing the root cause, when practical. - Apply the smallest safe fix after evidence confirms.
- VERIFY—Loop over every criterion declared in PLAN:
- Audit the task's own
git diff/git statusagainst the Self-cleanup checklist inreferences/cleanup-guide.md; remove every self-introduced artifact before proceeding. - For each unmet criterion: revert the fix, return to ACT, execute, then re-enter VERIFY.
- Exit only when all criteria pass.
- Halt only for out-of-scope blockers.
- Audit the task's own
- PERSIST—Write all fix artifacts once, atomically, after VERIFY passes. Never precedes VERIFY. Never partial.
- REPORT—Emit the result following the result directives and using the result template.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 150 lines · 20 tokens per session scan C e8630040bb12
troubleshoot is a skill published in the GitHub repository mystilleef/spae-framework (1 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 1,242 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ahk-triage
Triage a bug or unexpected behavior. Deep diagnostic analysis with structured report. No tasks created, no harness tracking.
ahk-ask
Ask a question about this codebase — where is X, does Y exist, how does Z work. Read-only. No tasks created, no harness tracking.
windows-encoding-fixes
Use when working with Windows (cmd/PowerShell console, MINGW64, script installation): stdout encoding (cp1251 vs UTF-8, UnicodeEncodeError on ✓/Cyrillic), CRLF/LF when writing files (md5 checks of mirrors), UTF-8 BOM for PowerShell 5.1, npm.cmd instead of npm, venv Scripts vs bin, PYTHONIOENCODING/PYTHONUTF8. Verified…
fix-and-verify
Diagnose a software defect, make the smallest compatible correction, and verify the affected behavior. Use for bugs, regressions, failing tests, and focused code changes.
debug-incident-protocol
Use when the user says: «it doesn't work», «still broken», «hung/stuck», «disappeared after the update», «it used to work», «the metric is zero but the UI is fine» — or when an incident needs to be analyzed, the root cause of a hang found, and whether a process was actually restarted verified. Covers: facts before…
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.