release-gate

release-gate is a skill for Claude Code, Codex from fireostendere/mcp_diptrace. It costs 42 tokens per session (677 once invoked), scanned A, original, Apache-2.0.

An evidence-based release check for DipTrace circuit designs. It reviews either a schematic or a PCB against the applicable checks and returns PASS or BLOCKED for the exact file version and review scope.

In plain words
What is it for?
Use it for the final release decision on a DipTrace design, covering electrical, board, manufacturing, assembly, testing, BOM, and thermal checks when available.
Why use it?
It prevents an apparently successful tool run from being mistaken for complete manufacturing or design approval, while exposing missing checks and remaining serious findings.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it for the final release decision on a DipTrace design, covering electrical, board, manufacturing, assembly, testing, BOM, and thermal checks when available.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fireostendere/mcp_diptrace/release-gate
Install

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.

Any agent
npx skills add fireostendere/mcp_diptrace --skill release-gate
Clone the repo
git clone --depth 1 https://github.com/fireostendere/mcp_diptrace

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for release-gate

README.md
[![agentmods](https://agentmods.dev/badge/skills/fireostendere/mcp_diptrace/release-gate.svg)](https://agentmods.dev/skills/fireostendere/mcp_diptrace/release-gate)
Your own site
<a href="https://agentmods.dev/skills/fireostendere/mcp_diptrace/release-gate"><img src="https://agentmods.dev/badge/skills/fireostendere/mcp_diptrace/release-gate.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 677 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.00677
Opus 5 $0.00021 $0.00338
Sonnet 5 $0.00008 $0.00135
Haiku 4.5 $0.00004 $0.00068

Measured 8d ago against content hash 67b0b6a8c6c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

release-gate 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 8d 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.

skills/release-gate/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release gate

Return PASS only for the exact requested revision and declared review scope. A green MCP run is not fab-house approval or DipTrace-format certification. Use public tools/list for exact callable names and get_capabilities for document/configured feature availability.

Workflow

  1. Call diptrace_status, get_capabilities, and get_document_info; record the exact SHA-256.
  2. Select profiles by document kind:
    • PCB: run_board_review, run_drc, run_connectivity_check, run_manufacturing_review, run_assembly_review, run_testability_review, run_bom_review, and run_thermal_review; supplement with analyze_release_readiness for bounded DFM/DFA/DFT findings available from exported XML (it supplements, not replaces, DipTrace sign-off).
    • schematic: run_schematic_review, run_erc, run_connectivity_check, and run_bom_review.
  3. Compare each result against the implemented/partial/missing matrix in REVIEW_ENGINE.md.
  4. Deduplicate by check ID and stable object identity. Preserve waivers, DNP state, explicit no-connects, confidence, approximation flags, and every skipped disclosure.
  5. Decide PASS only when no critical/error finding remains, all caller-mandatory implemented checks ran, the SHA stayed stable, and every unavailable category was accepted as outside scope.
  6. Otherwise decide BLOCKED and list the shortest evidence-producing next actions.
  7. Emit ../shared/result.schema.json; put the decision in summary and as a finding, not in the transport status.

Quantitative boundaries

  • Confidence is bounded from 0 through 1 but cannot overrule evidence class.
  • Results are paged/bounded; follow resource URIs and truncation metadata rather than assuming the first 100 findings are complete.
  • Document identity is a 64-character lowercase SHA-256.
  • The server's write limits are 100 operations and 500 conservatively counted affected objects/elements per write, but this gate is read-only.

Read the full file on GitHub · 52 lines

Changes

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.

  1. 8d ago First seen · 52 lines · 42 tokens per session scan A 67b0b6a8c6c4

Subscribe to this mod's changes

release-gate is a skill published in the GitHub repository fireostendere/mcp_diptrace (22 stars, last pushed 4d ago), licensed Apache-2.0. It adds 42 tokens to every session and 677 once invoked, about $0.0002 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.