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.
git clone --depth 1 https://github.com/yashs33244/the_y_coding_standardWrote 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/commands/yashs33244/the_y_coding_standard/y-ship)<a href="https://agentmods.dev/commands/yashs33244/the_y_coding_standard/y-ship"><img src="https://agentmods.dev/badge/commands/yashs33244/the_y_coding_standard/y-ship.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 | $0.00156 | $0.01529 |
| Opus 5 | $0.00078 | $0.00764 |
| Sonnet 5 | $0.00031 | $0.00306 |
| Haiku 4.5 | $0.00016 | $0.00153 |
Grade A, and why
y-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 6d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/y-ship
The "Ship." step. Step 07 of the Sprint Loop. /y-review said the code is right. /y-qa said the code works. /y-ship gets it out the door. This is not the place for new decisions. Every choice should already be made. This command runs the gates one more time, builds a clean PR, pushes, opens it, and tells you the URL. If any gate fails, it stops and tells you why.
Pre-flight
This is the strictest pre-flight in the loop. Do not skip any check.
1. Branch check
Run git branch --show-current. If the branch is main, master, trunk, or develop, abort hard. Ship from feature branches only.
2. Working tree check
Run git status --porcelain. If output is non-empty, ask the user: "Working tree is dirty. Commit WIP first, or abort?" If commit, generate a sensible commit message and commit. If abort, stop.
3. Active plan check
Look in plans/ for the active plan file. Read its frontmatter or header. Verify status: ready-to-ship. If status is anything else, abort and tell the user which step they skipped.
4. Review check
Look for findings/YYYY-MM-DD-review.md for today (or the most recent one tied to this branch). Parse the recommendation line. If recommendation is HOLD, abort. If there are any open P0 or P1 in the report, abort and list them. The user must run /y-review again after fixes.
5. QA check
Look for findings/YYYY-MM-DD-qa.md for today. Parse the verdict. If verdict is FAIL, abort. PASS or PASS WITH CONCERNS proceeds.
6. Date and folder check
Confirm today's date for filenames. Confirm progress/ exists; create if missing.
Workflow
1. Run governance
Invoke /y-govern as the final pre-flight gate. Wait for its output. If it reports any P0, abort and surface the P0 list. Do not ship around governance failures.
Load the right reference for context if governance flags stack-specific issues:
- Python:
references/python.md. - React / Next.js:
references/react-nextjs.md. - OOP issues:
references/oop.md. - Scaffold drift:
references/project-scaffold.md.
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.
- 6d ago First seen · 161 lines · 156 tokens per session scan A 631915c2af3d
y-ship is a command published in the GitHub repository yashs33244/the_y_coding_standard (2 stars, last pushed 3mo ago), licensed MIT. It adds 156 tokens to every session and 1,529 once invoked, about $0.0008 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 2026-08-31.
Other commands, from other repositories
land
Cadence-tick autonomous PR babysitter (CI-fix, resolve, converge, merge, close, release).
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
ship
Ship is the operational release-prep flow for a connected project repo.
release-plan
A release-planning command for a software change. It documents the release scope, rollback plan, gradual or full rollout, and monitoring before waiting for human approval.
release
Standalone SDK release command for the BUILD repo. Not a workspace phase — runs independently after any number of implement/redteam cycles. Handles PyPI publishing, documentation deployment, and CI management for the kailash Python SDK and its framework packages.
create-pr
Push the current branch and open a pull request into main with a structured description derived from the branch's commits and issue references.