finance-automation-portfolio: Skill for Claude Code

.claude/skills/ship/SKILL.md

ship is a skill for Claude Code from sophonfinance-wq/finance-automation-portfolio. It costs 36 tokens per session (523 once invoked), scanned A, original, MIT.

A release workflow for preparing code changes for the project's main branch. It creates a branch, runs the same package-level tests used by continuous integration (automated checks run after code changes), commits and pushes the work, opens a draft pull request, and waits for checks before merging.

In plain words
What is it for?
Use it to release completed work, test every package listed in the CI configuration, check the expected test count, and manage the branch and pull-request steps.
Why use it?
It reduces the risk of passing a local test while missing a package-specific failure or a required test-count check in CI.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is sophonfinance-wq/finance-automation-portfolio's own configuration. It tells Claude Code how to work on finance-automation-portfolio itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything finance-automation-portfolio configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sophonfinance-wq/finance-automation-portfolio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sophonfinance-wq/finance-automation-portfolio/main/.claude/skills/ship/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sophonfinance-wq/finance-automation-portfolio

Made for: Claude Code.

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 ship

README.md
[![agentmods](https://agentmods.dev/badge/skills/sophonfinance-wq/finance-automation-portfolio/ship/github.svg)](https://agentmods.dev/skills/sophonfinance-wq/finance-automation-portfolio/ship)
Your own site
<a href="https://agentmods.dev/skills/sophonfinance-wq/finance-automation-portfolio/ship"><img src="https://agentmods.dev/badge/skills/sophonfinance-wq/finance-automation-portfolio/ship/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.

agentmods 80×15 button for ship

Your own site · 80×15
<a href="https://agentmods.dev/skills/sophonfinance-wq/finance-automation-portfolio/ship"><img src="https://agentmods.dev/badge/skills/sophonfinance-wq/finance-automation-portfolio/ship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 523 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 $0.00036 $0.00523
Opus 5 $0.00018 $0.00262
Sonnet 5 $0.00007 $0.00105
Haiku 4.5 $0.00004 $0.00052

Measured 12d ago against content hash 8a751a390968, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ship 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 12d 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.

.claude/skills/ship/SKILL.md · 28 lines

What it actually says

Ship-It Workflow (this repo)

  1. Branch: work on the designated claude/... branch. If its PR already merged, restart it: git fetch origin main && git checkout -B <branch> origin/main.
  2. Test like CI (CI runs pytest per package, so a root pytest is NOT equivalent). Derive the package list from ci.yml rather than hardcoding it — a second copy silently goes stale every time an engine lands, and then "test like CI" quietly stops testing like CI:
    for d in $(sed -n 's/.*for dir in \(.*\); do.*/\1/p' .github/workflows/ci.yml | head -1); do
      (cd "$d" && python -m pytest -q) || echo "FAILED: $d"
    done
    
    SWEEP=1 enables the ~1.65M-case grids (skip for normal ships). Install deps once: pip install -r requirements.txt. Also confirm the count gate before pushing — CI's test-count.yml hard-asserts it and only runs on main, so a drift here fails after merge:
    python -m pytest --collect-only -q -m "not site_tooling" | tail -1   # must equal counts.json portfolio_curated
    
  3. Commit: imperative subject, body explains the why; never mention model IDs in artifacts.
  4. Push: git push -u origin <branch> (retry on network errors with backoff).
  5. PR: draft, mirror .github/pull_request_template.md (Summary + Review checklist — tests/CI, coverage, deterministic core, human-gated, no real data, docs).
  6. CI: workflow ci.yml, single test job, ~45-90s. Poll check runs; merge only on green.
  7. Merge (only with the user's standing approval): undraft, merge-commit method, then confirm the merged webhook closed the watch. GitHub Pages redeploys docs/ automatically after merge.
  8. Report outcomes faithfully: verdicts, test counts, what was quarantined/skipped.
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. 12d ago First seen · 28 lines · 36 tokens per session scan A 8a751a390968

Subscribe to this mod's changes

ship is a skill published in the GitHub repository sophonfinance-wq/finance-automation-portfolio (11 stars, last pushed 16d ago), licensed MIT. It adds 36 tokens to every session and 523 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.