Borrowing it
Nothing to install: this file belongs to nodealchemy/powernode-platform. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nodealchemy/powernode-platform/develop/.claude/skills/fix-tests/SKILL.mdgit clone --depth 1 https://github.com/nodealchemy/powernode-platformWrote 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/nodealchemy/powernode-platform/fix-tests)<a href="https://agentmods.dev/skills/nodealchemy/powernode-platform/fix-tests"><img src="https://agentmods.dev/badge/skills/nodealchemy/powernode-platform/fix-tests/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/nodealchemy/powernode-platform/fix-tests"><img src="https://agentmods.dev/badge/skills/nodealchemy/powernode-platform/fix-tests.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 | $0.00000 | $0.00725 |
| Opus 5.5 | $0.00000 | $0.00290 |
| Sonnet 5.5 | $0.00000 | $0.00145 |
| Haiku 4.5 | $0.00000 | $0.00072 |
Grade A, and why
fix-tests 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 1mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix Tests Workflow
Run the test suite for the given scope, diagnose failures, fix them, and re-run. The fixed parts are the 3-attempt limit per failure, the final re-run of the original scope, and the summary; how you diagnose each failure is your call (the Step 3 checklist lists common causes in this codebase).
Step 1: Determine Scope & Mode
Parse the argument to determine what to run:
backendor no argument →cd server && bundle exec rspec --format progressfrontend→cd frontend && CI=true npm teste2e→cd frontend && npx playwright test- A specific file path → run that file directly
Loop mode (--loop): Run the full fix cycle autonomously without asking for input. Make best-judgment fixes. Suitable for headless/unattended runs via claude -p "/fix-tests backend --loop".
Step 2: Run Tests
Execute the test command and capture output. Note all failures.
Step 3: Fix Loop (max 3 attempts per failure)
For each failing test:
- Read the failing spec file and the source file it tests
- Diagnose the root cause — check for:
- Missing factory traits (check
spec/factories/andspec/factories/ai/) - Wrong test helpers (use
user_with_permissions,auth_headers_for,json_response) - Missing shared examples (
spec/support/shared_examples/) - Missing mocks or stubs for external services
- Stale selectors in E2E tests (prefer
data-testid) - Import path issues (use
@/shared/,@/features/)
- Missing factory traits (check
- Fix the issue using Edit
- Re-run just the failing file to verify the fix
- If still failing after 3 attempts on the same test, stop and report — do not keep iterating
Step 4: TypeScript Check (frontend/e2e only)
If any TypeScript files were modified:
cd frontend && npx tsc --noEmit
Fix any type errors found (same 3-attempt limit).
Step 5: Final Run
Re-run the full suite for the original scope to confirm everything passes.
Step 6: Loop Mode Continuation (--loop only)
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.
- 1mo ago Changed · +2 lines a78bc4ea4465
- 2mo ago First seen · 72 lines · 0 tokens per session scan A a27c075b62b1
fix-tests is a skill published in the GitHub repository nodealchemy/powernode-platform (4 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 725 tokens. 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
unlimited-mcp-selftest
Run the unlimited-mcp regression battery (Tier 0 lint+types, Tier A automated, Tier B live end-to-end) and report pass/fail per step. Use when the user says "run the regression suite", "run the battery", "selftest", "test everything", or before a version bump. Requires the unlimited-mcp server connected…
tdd-workflow
Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
connect-agent
Connect the codebase's AI agent to LangWatch agent simulations, so test suites run against the real agent process. Adds a small connect function beside the service startup that calls the agent already in the codebase, which opens an outbound connection and registers the agent with its environment and its run…