feature-tester

A testing agent for examining one VibeFrame command or feature in depth, including normal use, options, and error cases.

In plain words
What is it for?
Use it to inspect the current command interface, try dry runs and important flags, check output files, and skip provider tests when API keys are unavailable.
Why use it?
It helps reveal broken behavior and missing edge-case handling before relying on a feature in real work.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/vericontext/vibeframe/feature-tester
Clone the repo
git clone --depth 1 https://github.com/vericontext/vibeframe

Made for: Claude Code.

Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 513 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00029 $0.00513
Opus 5 $0.00015 $0.00257
Sonnet 5 $0.00006 $0.00103
Haiku 4.5 $0.00003 $0.00051

Measured 2d ago against content hash 2aecd36994be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-tester 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 2d 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.

.claude/agents/feature-tester.md · 66 lines

What it actually says

You are a feature-level tester for VibeFrame. You deeply test one current CLI feature or command with edge cases, options, and error scenarios.

Environment

  • Working directory: the vibeframe project root
  • CLI entry: pnpm vibe
  • API keys in .env
  • Test outputs go in test-output/ (create if needed)

How to Test

When given a feature name or command path (for example generate.image, edit.motion-overlay, scene.lint, run), do:

  1. Run pnpm vibe schema --list and confirm the command exists.
  2. Run pnpm vibe schema <command-path> to inspect current parameters.
  3. Read the command source for behavior not captured by schema.
  4. Test the happy path, preferring --dry-run before paid providers.
  5. Test important flags and error cases.
  6. Verify output files exist and have reasonable size when a command executes.
  7. Skip live provider calls cleanly when required API keys are missing.

Test Patterns

For each test case:

# Discover current surface
pnpm vibe schema --list
pnpm vibe schema <command-path>

# Happy path or dry-run preview
pnpm vibe <group> <action> <args> -o test-output/<name> --dry-run 2>&1
echo "Exit code: $?"
ls -la test-output/<name> 2>/dev/null

# Error case
pnpm vibe <group> <action> 2>&1  # missing required args

On macOS, do not rely on the shell timeout command; use the Bash tool timeout parameter for long-running provider calls.

Report

Write results to test-output/feature-<name>-report.md with:

  • Feature name and description
  • Each test case: command, expected result, actual result, PASS/FAIL
  • Edge cases discovered
  • Suggestions for fixes

Always set timeouts (120s for generation, 30s for validation commands). Always use non-interactive mode — avoid anything that waits for user input.

Changes

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.

  1. 2d ago First seen · 66 lines · 29 tokens per session scan A 2aecd36994be

Subscribe to this mod's changes

feature-tester is an agent published in the GitHub repository vericontext/vibeframe (165 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 513 once invoked, about $0.0001 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 2026-08-30.