A shipping procedure for the PromptSpend project. It covers the checks and steps needed to move a branch through testing, pull-request review, merge, deployment, and live-site verification.

Use it when finishing a change, opening and merging a pull request, confirming CI, deploying, and checking the live site.

It prevents shipping untested or incomplete changes and distinguishes starting a deployment from confirming that it succeeded.

How AndrewAvery7/promptspend configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to AndrewAvery7/promptspend. 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/AndrewAvery7/promptspend/main/.claude/skills/ship/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/AndrewAvery7/promptspend

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/andrewavery7/promptspend/ship/github.svg)](https://agentmods.dev/skills/andrewavery7/promptspend/ship)

Your own site

<a href="https://agentmods.dev/skills/andrewavery7/promptspend/ship"><img src="https://agentmods.dev/badge/skills/andrewavery7/promptspend/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/andrewavery7/promptspend/ship"><img src="https://agentmods.dev/badge/skills/andrewavery7/promptspend/ship.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,259 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00082	$0.01259
Opus 5.5	$0.00033	$0.00504
Sonnet 5.5	$0.00016	$0.00252
Haiku 4.5	$0.00008	$0.00126

Measured 13d ago against content hash d345a95ee664, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 13d 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 · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ship a PromptSpend change

Andrew's standing approval (2026-10-06) covers merging and deploying this project's own work once its gate has genuinely passed. It does not cover skipping the gate, force-pushing, or any other repository. Merging publishes to promptspend.com, so say plainly when it has gone live.

Work through these in order. Stop and fix at any failure; never merge red.

1. Before pushing

Be on a feature branch cut from origin/main, not on main. git fetch, then confirm git merge-base --is-ancestor origin/main HEAD; if main has moved, bring the branch up to date first (in a worktree the app made for the session, use the sync_with_base_branch tool instead of merging by hand).
git status shows only the files this change meant to touch. Never stage referrers-*.json, .playwright-mcp/ or anything under .claude/worktrees/.
Run npm run verify from the repo root. It is the whole gate for the website and it is what CI runs. If the test count moved, run npm run check:test-badge -- --fix and commit what it rewrites.
If the change touches api/, worker/, mcp/, vscode/, updates/ or apps/mobile/, also run that package's own npm test: root verify does not run them (see the memory note "Package verify is not the whole gate").
If the change touches anything a visitor sees, run npx playwright test too, and look at the page in a browser at phone and desktop width, light and dark.

2. Open the pull request

Commit with a message that says what changed and why, ending with the attribution line the session was given. Push the branch.
gh pr create --base main --head <branch> --title "<title>" --body .... The body says what it adds, how it was checked, and anything Andrew must do afterwards; it ends with the attribution line the session was given.
In the Claude desktop app: ccd_pr get_status, bind_pr if it is not bound, then set_monitor with auto_fix and address_comments true.

Read the full file on GitHub · 103 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.

13d ago First seen · 103 lines · 82 tokens per session scan A d345a95ee664

Subscribe to this mod's changes

ship is a skill published in the GitHub repository AndrewAvery7/promptspend (1 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 1,259 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-07.

CI and CD DevOps and cloud Git and workflow LLM Releases ai-costs anthropic cloudflare-workers cost-estimator llm-pricing

deployment-patterns

Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.

affaan-m/ECC · 41 tokens

publish-site

Versioned site deploys to GitHub/Cloudflare/Netlify Pages.

NousResearch/hermes-agent · 19 tokens

github

GitHub via gh CLI: PRs, issues, reviews, repos, auth.

NousResearch/hermes-agent · 19 tokens

baby-sit

Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.

langchain-ai/open-swe · 30 tokens

swarm-migrate

Cross-repo migration swarm — one coordinator + N parallel subagents (one per target repo) that apply the same transformation, open PRs, wait for CI, and report back to a shared JSON ledger. Coordinator handles topology, conflict auto-rebase, and stop-on-novel-failure. Use when bumping a shared dependency, rolling out…

yonatangross/orchestkit · 103 tokens

gh-monitor-pr

Start a detached GitHub pull-request monitor that wakes the exact launching Codex Desktop or CLI root through the managed Codex App Server when review, CI, conflict, merge-queue, closure, readiness, or merge events need attention. Use when the user asks Codex to watch, monitor, babysit, or wait on a PR or merge queue…

closedloop-ai/claude-plugins · 81 tokens

promptspend: Skill for Claude Code