Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/vibeic/vibe-icnpx agentmods add skills/vibeic/vibe-ic/full-test-auditWrote 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/vibeic/vibe-ic/full-test-audit)<a href="https://agentmods.dev/skills/vibeic/vibe-ic/full-test-audit"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/full-test-audit/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/vibeic/vibe-ic/full-test-audit"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/full-test-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00145 | $0.01587 |
| Opus 5 | $0.00072 | $0.00794 |
| Sonnet 5 | $0.00029 | $0.00317 |
| Haiku 4.5 | $0.00015 | $0.00159 |
Grade A, and why
full-test-audit 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
full-test-audit — "have full test" = full test + D1 + D2 + D3
When the user says "have full test" (or "full test" / "run the full audit" / "check D1 D2 D3"), they do NOT mean "just run pytest". They mean this four-part plugin-health audit. Run ALL four and report each verdict; never report only the pytest number.
The split honours the program-first doctrine: the DETERMINISTIC dimensions live
in a program (programs/plugin_full_audit.py); only D3 (skill-rule
extractability) needs LLM judgment and is run as a fan-out here.
Part 1 — Full test (the CI way, not a subset)
./run_tests.sh IS the full suite. A bare pytest is NOT. pytest.ini
declares ONE testpath on purpose (single_testpath_guard.py pins it), so a bare
pytest reaches programs/tests and stops there. MEASURED at e37d10e1e that
leaves 141 of 3117 tracked test files unrun — skills/*/tests 82,
mcp-eda/test 48, tools/phase1_engine/tests 8, _shared 3 — while the 74
tiers run_tests.sh discovers leave none. This section used to instruct the
opposite ("bare pytest from the plugin root, single tree"), which is the
shortcut the owner-level ruling of 2026-08-31 closed:
full_suite_run_check.py now classifies an invocation by the population it
COVERS, so the command below is the one it accepts and the bare one is refused.
# chip-AGNOSTIC source guard (CI step 1a)
python3 <plugin>/programs/source_chip_agnostic_check.py <plugin>
# full suite (CI step 1b) — every tier, not one tree
cd <plugin> && ./run_tests.sh
# and confirm the command you actually ran counts as full:
python3 <plugin>/programs/full_suite_run_check.py --command "./run_tests.sh"
Report: passed / failed / skipped, and the guard verdict. A single FAILED is a
fail — surface the failing test, do not round it away. run_tests.sh prints the
tier census it discovered first; a tier count that has SHRUNK is itself a
finding, because the cheapest way to make a suite green is to stop running part
of it.
Part 2 — D1: every program has a test · Part 3 — D2: every step has a checker
What ships with it
2 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.
- 6d ago Changed · +12 lines 604d4cfa4059
- 10d ago First seen · 106 lines · 145 tokens per session scan A 1660e38c1578
full-test-audit is a skill published in the GitHub repository vibeic/vibe-ic (23 stars, last pushed today), licensed Apache-2.0. It adds 145 tokens to every session and 1,587 once invoked, about $0.0007 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 skills, from other repositories
analog-verify
Pre-simulation review and Spectre simulation verification for analog circuits. Reviews circuit netlist and testbench, runs simulation, produces margin report. Use after analog-design completes a netlist.
step6-verify
Step 6 · Per-module simulation verification (amnesia audit → human-confirmed plan → autonomous local-fix loop → full re-verify; escalate only when local options are exhausted).
boardrepo
Read and review real PCB projects on BoardRepo. Search published hardware designs, open a board's schematic connectivity, bill of materials and files, run KiCad's DRC and ERC, and check a design against a fabrication house's limits. Use whenever the user names a BoardRepo board or URL, asks to find a published board…
analog-netlist-crawl
Crawl and analyze post-layout parasitic netlists without running SPICE. Answers "what's the effective resistance from node A to node B across this massive R mesh?", "inside the VREFN mesh, which device pins are electrically farthest apart?", "which nets have the worst coupling?", "where does settling bottleneck?" — by…
analog-design
Transistor-level circuit design for one analog sub-block. Produces Spectre netlist with hand-calculation rationale. Use when designing a specific circuit block after architecture is defined.
analog-pipeline
MANDATORY — MUST load this skill when the user mentions: OTA, ADC, PLL, comparator, bandgap, LDO, amplifier, opamp, or any analog/mixed-signal IC design task. Full analog design pipeline: spec -> architecture -> design -> verify -> deliver. Orchestrates analog-decompose, analog-behavioral, analog-design…