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 skills add Himanshu-Sangshetti/cursor-stack --skill shipgit clone --depth 1 https://github.com/Himanshu-Sangshetti/cursor-stackWrote 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/himanshu-sangshetti/cursor-stack/ship)<a href="https://agentmods.dev/skills/himanshu-sangshetti/cursor-stack/ship"><img src="https://agentmods.dev/badge/skills/himanshu-sangshetti/cursor-stack/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.
<a href="https://agentmods.dev/skills/himanshu-sangshetti/cursor-stack/ship"><img src="https://agentmods.dev/badge/skills/himanshu-sangshetti/cursor-stack/ship.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00045 | $0.00809 |
| Opus 5.5 | $0.00018 | $0.00324 |
| Sonnet 5.5 | $0.00009 | $0.00162 |
| Haiku 4.5 | $0.00005 | $0.00081 |
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 1mo 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship - Release Engineer Mode
You are now in Release Engineer mode. The thinking is done. Your job is disciplined execution to land this code.
Your Mindset
- No more ideation or discussion
- Follow the checklist methodically
- Surface blockers immediately, don't hide them
- Momentum matters - get the code landed
Project Overrides
If @cursor-stack or AGENTS.md contains a cursor-stack section with mainBranch or testCommand, apply those values. Use mainBranch (e.g., main, master) for git rebase/diff commands instead of hardcoded main. Use testCommand for the test step instead of npm test.
Pre-Ship Checklist
Before shipping, verify:
[ ] All changes are intentional (git diff review)
[ ] No debug code or console.logs left behind
[ ] No commented-out code that should be removed
[ ] No secrets or credentials in the diff
[ ] Tests pass locally
[ ] Linting passes
Ship Process
Step 1: Sync with Main
git fetch origin
git rebase origin/main # or merge, based on project convention
If conflicts exist, resolve them carefully and verify the resolution.
Step 2: Run Tests
# Run the project's test command
npm test # or pytest, cargo test, etc.
If tests fail, stop and fix. Don't ship broken code.
Step 3: Final Diff Review
git diff origin/main --stat # Overview of changes
git diff origin/main # Full diff
Quick scan for:
- Accidental file inclusions
- Debug statements
- Anything that shouldn't ship
Step 4: Commit (if needed)
If there are uncommitted changes:
git add -A
git commit -m "<type>(<scope>): <description>"
Commit message format:
feat: New featurefix: Bug fixrefactor: Code change that neither fixes nor addsdocs: Documentationtest: Adding testschore: Maintenance
Step 5: Push
git push origin HEAD
# or for new branches:
git push -u origin HEAD
Step 6: Create PR
gh pr create --title "<title>" --body "## Summary\n- What this PR does\n\n## Changes\n- Key changes\n\n## Testing\n- How tested"
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.
- 1mo ago First seen · 142 lines · 45 tokens per session scan A b6819fd69152
ship is a skill published in the GitHub repository Himanshu-Sangshetti/cursor-stack (8 stars, last pushed 7mo ago), licensed MIT. It adds 45 tokens to every session and 809 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
deploy-npm
Release an npm package: version, CHANGELOG, publish, verify. Use when "publish this package", "release to npm", or "ship a new npm version". Running-app production deploy → workflow-ship-and-observe.
cognitive-version-snapshot
A controlled process for saving a major new version of a system document as a dated snapshot.
actions-reusable-workflows
Wire a repository to the bitwise-media-group/github-workflows reusable workflows — thin, SHA-pinned caller workflows for CI, security (CodeQL) scanning, release (release-please/GoReleaser/Zensical docs), the signature-preserving fast-forward /merge + merge-review-ack + merge-notice flows, and add-to-project — plus the…
project-release
Cut a release of this project (maven-decoder-mcp): draft notes, verify the gate, tag, push, watch CI, and confirm packages on PyPI, npm, Docker Hub, and GitHub. Use when the user says "release", "cut a release", "ship it", "tag a version", or asks about the release process, release notes, or publishing.
housekeep-dead-code
Remove dead code by category — one commit each, typecheck and tests between, bisect on red — then add a Knip ratchet. Use when "delete the dead code", "remove unused files", or "wire up Knip". Audit first → plan-dead-code. README/deps → workflow-housekeep.
burndown-full
Drive a planned mechanical change to 100% repo coverage after a run stopped early. Use when "finish the burndown", "it stopped halfway", "apply this everywhere", or "half-migrated". One plan plus deferrals → complete-everything.