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 agents/vericontext/vibeframe/feature-testergit clone --depth 1 https://github.com/vericontext/vibeframeWhat 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 | $0.00029 | $0.00513 |
| Opus 5 | $0.00015 | $0.00257 |
| Sonnet 5 | $0.00006 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00051 |
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.
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:
- Run
pnpm vibe schema --listand confirm the command exists. - Run
pnpm vibe schema <command-path>to inspect current parameters. - Read the command source for behavior not captured by schema.
- Test the happy path, preferring
--dry-runbefore paid providers. - Test important flags and error cases.
- Verify output files exist and have reasonable size when a command executes.
- 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.
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.
- 2d ago First seen · 66 lines · 29 tokens per session scan A 2aecd36994be
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.
Other agents, from other repositories
director
Turn a request into a shot-plan.json for a short (3–30s) design-led motion graphic. You run in two parts around the asset-sourcing step: Part 1 (plan) before sourcing, Part 2 (design) after. You do NOT write composition code — that's the Builder. Schema: references/shot-plan-ir.md.
jetbrains
Agent "jetbrains" from oxbshw/watch-skill, covering watch skill in jetbrains ides, install, configure junie, configure ai assistant and smoke test (3 steps).
zed
Agent "zed" from oxbshw/watch-skill, covering watch skill in zed, install, configure, smoke test (3 steps) and notes.
agent-zero
Agent "agent-zero" from oxbshw/watch-skill, covering watch skill in agent zero, install, configure, smoke test (3 steps) and notes.
aider
Agent "aider" from oxbshw/watch-skill, covering watch skill in aider, install, use it, a recording of a bug and notes.
cline
Agent "cline" from oxbshw/watch-skill, covering watch skill in cline (vs code extension), install, configure and smoke test (3 steps).