Borrowing it
Nothing to install: this file belongs to andrewbartels1/SolidworksMCP-python. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/andrewbartels1/SolidworksMCP-python/main/.claude/skills/openspec-proposal-auditor/SKILL.mdgit clone --depth 1 https://github.com/andrewbartels1/SolidworksMCP-pythonWrote 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/andrewbartels1/solidworksmcp-python/openspec-proposal-auditor)<a href="https://agentmods.dev/skills/andrewbartels1/solidworksmcp-python/openspec-proposal-auditor"><img src="https://agentmods.dev/badge/skills/andrewbartels1/solidworksmcp-python/openspec-proposal-auditor.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00103 | $0.02856 |
| Opus 5 | $0.00051 | $0.01428 |
| Sonnet 5 | $0.00021 | $0.00571 |
| Haiku 4.5 | $0.00010 | $0.00286 |
Grade A, and why
openspec-proposal-auditor 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: OpenSpec Proposal Auditor
Audit the planning artifacts of an OpenSpec change for clarity, conciseness,
scope discipline, and — critically — factual accuracy against ground
truth: the actual repo (code, tests, docs) and the actual state of any
GitHub issues/PRs the artifacts reference. This is a read-only review. It
never edits change artifacts; it produces findings and a concern register
for the user (or /opsx:update) to act on.
Gate, not a formality. The point of this skill is to catch stale or
invented claims before design.md/tasks.md get treated as ready to
implement — this repo has a documented history of exactly that problem
(see openspec/changes/close-tool-surface-gaps-and-housekeeping/proposal.md
for a real example: three issues turned out to be already partly shipped
by merged PRs the issue text didn't know about). A proposal that "reads
well" is not the bar. A proposal whose every checkable claim has been
checked, is.
When to run this
- Before running
/opsx:applyon a change — always, not just on request. - Immediately after any
/opsx:updaterevision to the same change. - On explicit request ("audit this proposal", "check the proposal for issue #NN", "run the proposal auditor").
Selecting the change
If a change name is given, use it. Otherwise run openspec list --json,
and if more than one change exists, list the 3-4 most recently modified
and ask the user to pick (same convention as /opsx:update). Announce
"Auditing change: ".
Procedure
Work through the steps in order. Do not skip Step 1 to jump to scoring — the scoring in Step 2 depends on the verification table Step 1 produces, and the Concern Register in Step 3 depends on both.
Step 0 — Load everything
openspec status --change "<name>" --jsonfor artifact paths and state.- Read every existing artifact in full:
proposal.md, everyspecs/**/*.md,design.md,tasks.md. Read from disk, not from conversation memory, even if you authored them earlier this session. - Read
openspec/config.yaml(oropenspec/project.mdif this store uses that filename) for the project's own stated context and conventions — this is the baseline Step 2's Drift check compares against. - Read
CLAUDE.mdat the repo root for architecture/convention ground truth not captured in the openspec config.
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 · 222 lines · 103 tokens per session scan A 427351efd999
openspec-proposal-auditor is a skill published in the GitHub repository andrewbartels1/SolidworksMCP-python (70 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 2,856 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.