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/catalog-glue-authorWrote 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/catalog-glue-author)<a href="https://agentmods.dev/skills/vibeic/vibe-ic/catalog-glue-author"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/catalog-glue-author/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/catalog-glue-author"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/catalog-glue-author.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 | $0.00118 | $0.04484 |
| Opus 5 | $0.00059 | $0.02242 |
| Sonnet 5 | $0.00024 | $0.00897 |
| Haiku 4.5 | $0.00012 | $0.00448 |
Grade A, and why
catalog-glue-author 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 4d 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 — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.
catalog-glue-author — Plugin IP integrator path
When this skill fires
When design_one_shot_runner.step_rtl_gen returns:
WAIVED rtl_gen — IC class registered but rtl_gen=null.
Recommended action: AI invokes skill `catalog-glue-author`.
IP catalog matches found (evidence — the recommended skill is the one named in
`Recommended action` above; ...):
- cpu/serv v1.4.0 (ISC) confidence=0.5; matched: ...
- cpu/picorv32 v1.0.0 (ISC) confidence=0.5; matched: ...
RB2-01 (#2063): a catalog match on its own does NOT hand the design to this
skill. The IC class registry's own fallback_skill stands unless the INPUT
docs name the matched IP as this design's reuse; when they do not, the WAIVE
names spec-to-rtl and the matches are printed as evidence only. The match
list a run acted on is in
...extras.ip_catalog_declared_reuse (which matches were declared reuse) beside
extras.ip_catalog_matches (everything the query returned).
Plus phase2_one_shot.json.steps[name=rtl_gen].extras.ip_catalog_matches carries the structured match list.
This is the Plugin SoC class path identified by the strict-blind pilot finding: complex IPs (CPUs, large SoCs) cannot be reverse-engineered from 9-document spec. Plugin INSTEAD selects pre-validated open-source IPs from the catalog and authors only the integration wrapper.
What this skill does
┌─────────────────────────────────────────────────────────────────┐
│ 1. Read project/reports/orchestrator/phase2_one_shot.json │
│ extract rtl_gen.extras.ip_catalog_matches │
│ │
│ 2. Re-rank if needed; user may override which IPs to include │
│ │
│ 3. For each selected IP, invoke ip_catalog_pull.py: │
│ - Locate local mirror OR git clone canonical_url@commit │
│ - License compliance check (reject GPL/AGPL/SSPL) │
│ - Copy listed rtl_files to project/phase2/stage1/rtl/ │
│ - Compute SHA256 of each pulled file │
│ - Append provenance.jsonl record │
│ │
│ 4. Read input/docs/L3 + L8 to determine chip-top wrapper │
│ port contract + sub-module instantiation pattern │
│ │
│ 5. AI-author the chip-top wrapper (typically 50-300 LOC): │
│ - Module declaration matching L3 ports │
│ - Instantiations of pulled IPs │
│ - Memory-mapped register decoder if L4/L5 needed │
│ - Wishbone / AXI / custom bus adapters per L8 spec │
│ - Reset polarity + clock distribution per L3 │
│ │
│ 6. Update project/plugin_output/declaration.json: │
│ "rtl_strategy": "catalog_lookup_plus_ai_glue", │
│ "ip_catalog_used": [...full audit per pull...], │
│ "ai_authored_files": ["my_chip_top.v", ...], │
│ "license_compliance_audit": { │
│ "all_permissive": true, │
│ "spdx_set": ["ISC", "Apache-2.0", ...] │
│ } │
│ │
│ 7. Re-run phase2 downstream steps (reference_tb / yosys / │
│ sdc_gen) to verify integration compiles + meets spec │
└─────────────────────────────────────────────────────────────────┘
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.
- 4d ago Changed · +9 lines 38cb033c9f12
- 12d ago First seen · 318 lines · 118 tokens per session scan A 9921d982b393
catalog-glue-author is a skill published in the GitHub repository vibeic/vibe-ic (23 stars, last pushed today), licensed Apache-2.0. It adds 118 tokens to every session and 4,484 once invoked, about $0.0006 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-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"…
analog-decompose
Architect Phase 1: decompose top-level analog spec into sub-block specs. Use when starting a new analog design to select architecture, allocate budgets, define sub-block specs, write testbenches, and create verification plans.