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/community-backlog-submitWrote 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/community-backlog-submit)<a href="https://agentmods.dev/skills/vibeic/vibe-ic/community-backlog-submit"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/community-backlog-submit/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/community-backlog-submit"><img src="https://agentmods.dev/badge/skills/vibeic/vibe-ic/community-backlog-submit.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 327 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 | $0.00060 | $0.04147 |
| Opus 5 | $0.00030 | $0.02073 |
| Sonnet 5 | $0.00012 | $0.00829 |
| Haiku 4.5 | $0.00006 | $0.00415 |
Grade A, and why
community-backlog-submit 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 9d 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 — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Community Backlog Submit — Organic Plugin Contribution
Purpose
When a bug is found in the generated RTL (via simulation, hardware test, or manual review), the agent's job is NOT to just fix the bug — it must also look back at the plugin and ask:
"Could the current plugin have caught this bug BEFORE it reached hardware? If not, what general enhancement would catch this entire CLASS of bugs in the future?"
This skill records that enhancement opportunity — not the bug itself — as a structured, IC-agnostic backlog item that can be contributed back to the Vibe-IC community.
Where this fits — the public contribution model (Layer 1). A backlog is the report-only half of Vibe-IC's public contribution model: you found a gap but are not carrying a fix. The other half is a PR (report-with-fix). Both are valid; the merged repo-gatekeeper / maintainer triages backlogs and reviews + lands PRs into the next plugin version. (The maintainer's own in-house fixes land by direct push — that internal shortcut is not the contributor path; as a contributor you file a backlog or a PR, you do not push to
main.)
The fix-all-into-the-plugin principle
When you report a backlog / find an issue, the expectation is NOT to triage it into a category and then decide whether it is "worth" fixing. Every issue gets fixed, and the fix lands in the next version of the vibe-ic plugin — it does not matter whether the fix lives in a deterministic program, an MCP tool, or a skill. The category is an implementation detail of where the fix goes, never a reason to skip the fix.
- Do not discard an issue as "not a plugin gap", "design-side", "clean-room variance", "spec ambiguity", or "the author should have known". If a fresh user could hit it, the plugin must handle it next time.
- A recovery that currently relies on a skill-prose lesson a fresh author might forget is itself an enhancement: promote it to a deterministic program (program-first) so it fires every time, automatically.
- The honest discard bucket is reserved only for a fix that is genuinely non-generalizable (it would over-fit one design's quirk or peek at a hidden oracle) — and even then you record why, you do not silently drop it.
Convergence test (loop-until-dry): a benchmark / flow close-loop has converged only when a fresh clean-room re-run on the newest plugin produces 0 residual that needs a plugin fix. As long as a clean-room run still surfaces any recoverable residual, the loop is not done: capture it → fix it into the plugin → re-run. One round with zero new backlog is a candidate; two consecutive zero-backlog clean-room rounds is convergence.
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.
- 9d ago First seen · 359 lines · 60 tokens per session scan A 7067e0ccd5c1
community-backlog-submit is a skill published in the GitHub repository vibeic/vibe-ic (23 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 4,147 once invoked, about $0.0003 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
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-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-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-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"…