Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/intelligentelectron/universal-netlist/releasenpx skills add IntelligentElectron/universal-netlist --skill releasegit clone --depth 1 https://github.com/IntelligentElectron/universal-netlistWhat 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 | $0.00064 | $0.01384 |
| Opus 5 | $0.00032 | $0.00692 |
| Sonnet 5 | $0.00013 | $0.00277 |
| Haiku 4.5 | $0.00006 | $0.00138 |
Grade A, and why
release scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Committing
Include ALL changes
The user works in parallel with you. When asked to commit, include ALL changes in the working tree, not just the ones you made. The user's manual edits are equally important. Always run git status first and review everything.
Workflow
- Run
git status(never use-uall) andgit diff --statto see the full picture - Run
git log --oneline -5to match the repository's commit message style - Review ALL changes, both yours and the user's, to understand the full scope
- Stage ALL relevant files. Do not cherry-pick only your changes
- Do NOT stage files that contain secrets (
.env, credentials, keys) - Warn the user if they ask to commit such files
- Do NOT stage files that contain secrets (
- Draft a commit message:
- Format:
type: description(e.g.,feat:,fix:,chore:,refactor:,docs:,test:) - Focus on the "why", not the "what"
- Keep it concise (1-2 sentences)
- Format:
- Commit using a HEREDOC for clean formatting:
git commit -m "$(cat <<'EOF' type: description EOF )" - NEVER add Claude Code or any other AI assistant as co-author or author
- NEVER use
--no-verifyto skip hooks unless the user explicitly asks - If pre-commit hooks fail, fix the issue and create a NEW commit (do not amend)
Grouping commits
For large changesets, plan multiple logical commits. After the first commit passes hooks cleanly, subsequent commits can use --no-verify to speed things up.
Pushing
- Push without asking. The PR and its checks are the review gate, not a confirmation prompt
- Use
git pushfor tracked branches - Use
git push -u origin <branch>for new branches - NEVER force push to
main/master
Merging
If a PR's work is fully done and verified, merge it. Do not leave finished work sitting open waiting for permission, and do not ask whether to merge something that is complete and green.
Done and verified means: the change does what the PR says, build is green, and any
claim the PR makes about behavior has been checked against real data rather than asserted.
A PR that is still exploratory, or whose effect has not been measured, is not done — say
what is missing instead of merging it.
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.
- 2d ago First seen · 123 lines · 64 tokens per session scan A 1f80caef2084
release is a skill published in the GitHub repository IntelligentElectron/universal-netlist (31 stars, last pushed 4d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,384 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
autodesign
Drive an autonomous spec-to-board PCB design with the eda-agent MCP server (Altium Designer or EasyEDA Pro). Apply when the user asks to design a board/schematic from a requirement, wants an end-to-end autonomous design run, or mentions the design harness, designnextaction, design sessions, or spec-to-board. Requires…
release
Prepare a new version release for the openroad-mcp project. Automates version bumping, changelog generation, lockfile updates, and release commit creation. Use this skill whenever the user asks to: Prepare a release, cut a release, or do a release Bump the version or update the version Create a release commit Ship a…
altium-library
Create and verify Altium schematic symbols (.SchLib) and PCB footprints (.PcbLib) from datasheets and 2D drawings, as code. Use whenever a part library must be made, fixed, measured from a drawing, or checked. Triggers: "make a footprint", "create a symbol", "add this part to the library", "SchLib", "PcbLib"…
altium-pcb-placement
Altium PCB component placement — derive board size, decide rotation for main ICs and connectors, split zones, generate a 1:1 placement plan drawing, then inject real coordinates after approval, and check overlaps. Triggers: "PCB placement", "place the components", "how big should the board be", "board outline", "start…
altium-schematic-review
Review an Altium schematic (.SchDoc) — find unconnected pins, missing footprint links and net errors, then judge each candidate against the datasheet before calling it a defect. Triggers: "review this schematic", "check my circuit", "ERC", "floating pins", "unconnected", "any missing footprints", "does this schematic…
zaptrace-design-validation
Validate a local ZapTrace design with requirements review, ERC/DRC evidence, and bounded engineering risk reports without claiming fabrication approval.