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 agentmods add skills/smart-ai-memory/attune-ai/fix-testnpx skills add Smart-AI-Memory/attune-ai --skill fix-testgit clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWrote 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/smart-ai-memory/attune-ai/fix-test)<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/fix-test"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/fix-test.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 | $0.00047 | $0.00574 |
| Opus 5 | $0.00023 | $0.00287 |
| Sonnet 5 | $0.00009 | $0.00115 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
fix-test 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 6d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix Test
IMPORTANT: Start your response with a context preamble.
Call help_lookup(topic="fix-test", mode="preamble") and
display the returned preamble text as a blockquote. Then
tell the user they can say "tell me more" for a step-by-step
guide, or answer the scoping questions below to proceed.
If the MCP call fails, fall back to:
Fix Test — Diagnoses failing tests, classifies the root cause, and applies targeted fixes automatically.
Scoping
Before running, ask:
- Target: "Which test is failing? A specific file, test name, or should I find failures automatically?"
- Context: "Did this start failing after a recent change, or has it been broken?"
Execution
Step 1: Identify Failures
Run the failing test(s) to capture the error:
uv run pytest <target> -v --tb=short 2>&1 | tail -40
Step 2: Diagnose Root Cause
Common failure patterns:
| Pattern | Root Cause | Fix |
|---|---|---|
ModuleNotFoundError |
Import path changed | Update import |
AttributeError: mock |
Mock target wrong | Match import path |
AssertionError |
Expected value drift | Update assertion |
TypeError: __init__ |
Constructor changed | Update call site |
FileNotFoundError |
Fixture path wrong | Use tmp_path |
Step 3: Apply Fix and Re-run
Apply the fix, then re-run the test. If it still fails, diagnose again with the new error. Repeat up to 3 times.
uv run pytest <target> -v --tb=short
Step 4: Report
After fixing (or exhausting 3 attempts), report:
## Fix Test Results
**Tests Fixed:** X/Y | **Attempts Used:** Z/3
### Fixed
| Test | Root Cause | Fix Applied |
|------|------------|-------------|
### Still Failing (if any)
| Test | Error | Attempts | Notes |
|------|-------|----------|-------|
Follow-Up
After presenting results, offer:
- "Want me to generate missing tests for the fixed module?"
- "Should I check for similar failures elsewhere?"
- "Want a deeper look at the root cause?"
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.
- 6d ago First seen · 84 lines · 47 tokens per session scan A f0608ccfc642
fix-test is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 574 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
novel-check
LLM 连通性自检:对默认模型与各角色模型做一次最小真实调用,逐一报告 provider/model 是否真的可用。触发:「检查 LLM 能不能用」「测试模型连通」「创作前先确认配置」「为什么一调用就报错」,排查代理未启动 / key 失效 / baseurl 写错时使用。.
novel-diag
诊断当前项目的 output 产物,从流程/质量/规划/上下文四维给出可执行发现,并写出脱敏报告。触发:「诊断这本书」「为什么卡住了」「检查创作有没有问题」「生成 diag 报告贴 issue」。.
ci-repair
Fix CI failures by fetching GitHub Actions logs, dispatching dev to fix, verifying locally, and pushing.
debugging-discipline
Дисциплина отладки: стоп-линия при сбое, воспроизводящий тест до фикса, первопричина вместо симптома, минимальная правка, защита от регрессии.
error-handling-discipline
Дисциплина ошибок: ловим ожидаемые исключения (LLMError/ToolError/TimeoutError), нет необработанных, пользователю — человеческое сообщение, stacktrace только в лог.
massgen-log-analyzer
Run MassGen experiments and analyze logs using automation mode, logfire tracing, and SQL queries. Use this skill for performance analysis, debugging agent behavior, evaluating coordination patterns, and improving the logging structure, or whenever an ANALYSISREPORT.md is needed in a log directory.