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/phase1-coverage-loopWrote 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/phase1-coverage-loop)<a href="https://agentmods.dev/skills/vibeic/vibe-ic/phase1-coverage-loop"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/phase1-coverage-loop/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/phase1-coverage-loop"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/phase1-coverage-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 172 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00150 | $0.04426 |
| Opus 5 | $0.00075 | $0.02213 |
| Sonnet 5 | $0.00030 | $0.00885 |
| Haiku 4.5 | $0.00015 | $0.00443 |
Grade A, and why
phase1-coverage-loop 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 — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Phase 1 Coverage Loop — Closed-Loop Phase 1 Ingester Improvement
Purpose
field-agent-loop covers Phase 1 / 2 / 3 — it drives plugin
quality on the existing-design-documents entry path. This
sibling skill closes the same loop for the prompt/dialogue
entry path (Phase 1).
The loop treats benchmark IC README files as realistic Phase 1
prompts: an experienced user briefing the platform would mention
the same facts the README documents (clock rate, supply voltage,
register addresses, pin names, opcodes, timing). After running
/vibe-ic-phase1 on each IC, the completeness gate harvests
chip-AGNOSTIC design tokens from the prompt and verifies each
token survived into generated_docs/L*.json, human_docs/L*.md,
facts.yaml, or PROVENANCE.md. Missing tokens are systematic
ingester gaps — they become backlog issues.
The loop is chip-AGNOSTIC: filed issues describe general
ingester gaps (e.g. "NL ingester drops <pattern> register-table
rows"), never project-specific bugs. Every YAML passes
backlog_sanitize_check before filing.
State
<target>/_field_agent_phase1_state.json
Schema:
{
"step": 1 | 2 | 3 | 4 | "STOPPED",
"iter": <int>,
"started_at": "<YYYY-MM-DD>",
"target_folder": "<absolute path to benchmark folder>",
"ic_rotation": ["<ic_name>", "<ic_name>", ...],
"current_ic_index": <int>,
"rotation_passes_completed": <int>,
"last_plugin_version": "<semver>",
"agent_task_id": "<id or null>",
"agent_status": "<short status string>",
"issue_number": <int or null>,
"tracking_secondary": [<int>, ...],
"per_ic_last_verdict": {"<ic_name>": "PASS|WARN|FAIL|SKIP", ...},
"last_summary": "<one paragraph>"
}
ic_rotation construction and advance/wrap are enforced by
programs/phase1_rotation_state_advance.py (no longer hand-rolled):
# build the rotation (sorted immediate subdirs with README.md or input/prompt.md)
python3 programs/phase1_rotation_state_advance.py build --target <target> --json rot.json
# advance the index by one; wrap → rotation_passes_completed += 1
python3 programs/phase1_rotation_state_advance.py advance \
--current-index <i> --count <len> --passes <p> --json adv.json
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 First seen · 396 lines · 150 tokens per session scan A 3993bd159bc5
phase1-coverage-loop is a skill published in the GitHub repository vibeic/vibe-ic (23 stars, last pushed today), licensed Apache-2.0. It adds 150 tokens to every session and 4,426 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 2026-09-03.
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.
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…
analog-audit
Audit analog circuit netlists for correctness, quality, and risks. Supports both pre-layout (schematic) and post-layout (extracted) netlists. Post-layout mode filters massive parasitic netlists before auditing. Works without EDA. TRIGGER on: "audit", "review netlist", "check this circuit", "design review"…