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/checkpoint-gateWrote 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/checkpoint-gate)<a href="https://agentmods.dev/skills/vibeic/vibe-ic/checkpoint-gate"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/checkpoint-gate/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/checkpoint-gate"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/checkpoint-gate.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 | $0.00082 | $0.04388 |
| Opus 5 | $0.00041 | $0.02194 |
| Sonnet 5 | $0.00016 | $0.00878 |
| Haiku 4.5 | $0.00008 | $0.00439 |
Grade A, and why
checkpoint-gate scanned grade A with 1 finding 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 5d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
`subprocess.Popen(cmd, cwd=str(project))`, which DISCARDS the working directory How it starts
The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Case-study notation. This skill cites the / / MDV-A1101 reference project as concrete evidence for the rules below. The rules themselves are chip-AGNOSTIC and apply to any IC of the matching
ic_class(seevibe-ic-marketplace/plugins/vibe-ic/programs/ic_class_profile.py). When you adopt this skill on a different IC, swap<chip-class>→<your IC name>and<half-duplex-tester>→<your host-tester name>; the structural gates and rule bodies do not depend on those SKUs. Seedocs/design/CASE_STUDIES/AS3616_*.mdfor the full regression history.
Checkpoint Gate — Phase Transition Verification
⚠️
checkpoint_gate_check.pyHAS ROTTED — DO NOT RUN IT AS A GATE (vibe-ic#693)This document used to instruct an agent to run
checkpoint_gate_check.pyand act on its verdict. That program now FAILS 46 of 46 run trees on a working checkout at all three checkpoints — 138 of 138 invocations, and every red is path rot, not a defect. It addresses a directory layout the flow abandoned (phase1_spec/*instead ofphase1/generated_docs/), and two of its sub-checks actively mis-read a healthy run: the CP2 required-file glob for RTL resolves to the formal file ([PASS] file:rtl → phase2/stage1/formal/formal_spm.sv— a false MATCH, not a false miss), andcell_countreports0 cell(s)on a run that placed real cells.An agent following the instruction below will be told a healthy design cannot advance. Acting on that verdict is wrong; so is learning to ignore a gate.
REPLACED BY the per-step gate set, which is what the flow actually runs:
this checkpoint asks the flow already answers with CP1 L-doc presence phase1_doc_presence_check(the one sub-check here that still passes)CP2 synth / DEF / GDS / DRC flow steps 14 / 16 / 31 / 37 — gds_substance_check,drc_report_check,provenance_checkCP3 FPGA sign-off step 37 + the FPGA cap-gap waiver machinery The program is recorded in
programs/checker_execution_wiring_baseline.json :: unwired_by_decisionwith the full measurement, andchecker_execution_wiring_auditre-derives that claim on every CI run — so if anything ever wires it, CI says so instead of licensing it silently. Repairing it means rewriting the checklist against the current layout (or deleting it), not wiring it.Use the per-step gates below the fold for the phase-transition question.
What ships with it
3 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.
- 5d ago Changed 86bf948f4fa5
- 9d ago First seen · 334 lines · 82 tokens per session scan A 6808e0a390b0
checkpoint-gate is a skill published in the GitHub repository vibeic/vibe-ic (23 stars, last pushed today), licensed Apache-2.0. It adds 82 tokens to every session and 4,388 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
status
Show flow status: current step, open issues, and the next command to run.
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-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.
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"…