What is push-and-watch?

A deployment workflow that follows a code push through to the running site. It checks what commits are included, asks for approval, watches the deployment, verifies the live result, and identifies how to roll back.

It helps prepare and monitor production pushes, inspect migrations and dependency changes, confirm live behaviour, and plan a rollback.

It prevents a push from being treated as finished before the deployed system has been checked, especially when migrations or dependency changes limit rollback options.

push-and-watch — Skill for Claude Code by yash-gadodia/claude-init

Install

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.

Any agent

npx skills add yash-gadodia/claude-init --skill push-and-watch

Clone the repo

git clone --depth 1 https://github.com/yash-gadodia/claude-init

Made for: Claude Code.

Or install claude-init, the plugin that ships this one along with the rest of its 17 skills, 1 command, 7 agents.

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/yash-gadodia/claude-init/push-and-watch/github.svg)](https://agentmods.dev/skills/yash-gadodia/claude-init/push-and-watch)

Your own site

<a href="https://agentmods.dev/skills/yash-gadodia/claude-init/push-and-watch"><img src="https://agentmods.dev/badge/skills/yash-gadodia/claude-init/push-and-watch/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/yash-gadodia/claude-init/push-and-watch"><img src="https://agentmods.dev/badge/skills/yash-gadodia/claude-init/push-and-watch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 790 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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	$0.00072	$0.00790
Opus 5.5	$0.00029	$0.00316
Sonnet 5.5	$0.00014	$0.00158
Haiku 4.5	$0.00007	$0.00079

Measured 1mo ago against content hash 75fed7b6383c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

push-and-watch scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`curl -s -H 'Cache-Control: no-cache' '<LIVE_URL>?cb=$(date +%s)' | grep '<changed text>'` and report the matched string. Then run the live-verify pass on production for the behavior that shipped. If the deploy succeeded

templates/skills/push-and-watch/SKILL.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Push and watch

<DEPLOY_TRIGGER: e.g. "A push to origin/main deploys production through ."> The push is not the end of the work: it starts a chain that ends with live evidence, and whoever pushes owns the whole chain.

1. Read what rides along

git log --format='%h %(trailers:key=Claude-Session,valueonly,separator=) %an %s' origin/<DEFAULT_BRANCH>..HEAD

Other people's and other sessions' commits deploy with yours. The Claude-Session: trailer (stamped by .githooks/prepare-commit-msg) says which session wrote each one. For every commit, know what it is and whether it carries a migration or a dependency change.

Keep migrations and dependency upgrades in separate pushes. A push with only code changes can be rolled back by redeploying the previous build. A push with a migration can only be fixed forward, because the schema has already moved. Put a risky dependency bump in the same push as a migration and you lose the rollback exactly when you need it.

2. Confirm, per push

Tell the user the commit count, anything not built in this session, and whether a migration or dependency change rides. Approval for an earlier push does not carry over. Preconditions: clean tree, gate green on the rebased tree.

3. Push, then watch to the end

git push origin <DEFAULT_BRANCH>, then <WATCH_CMD: e.g. gh run watch <id> --exit-status, railway deployment list, vercel inspect>. A red build means nothing deployed; read the failing output rather than re-pushing.

4. Verify live, immediately

curl -s -H 'Cache-Control: no-cache' '<LIVE_URL>?cb=$(date +%s)' | grep '<changed text>' and report the matched string. Then run the live-verify pass on production for the behavior that shipped. If the deploy succeeded but the change is not visible, say so (likely a CDN cache) instead of claiming success. Tell every other session whose commits rode along that the deploy is live.

5. If it is bad

No migration rode: <ROLLBACK_CMD: e.g. redeploy the previous deployment in the host's dashboard/CLI, or git revert + push>.
A migration rode: fix forward with a new commit. Rolling the code back would run old code against the new schema.
Repair data damage with a reviewed, hand-run script, never with a follow-up migration written in a hurry.

Read the full file on GitHub · 54 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.

1mo ago First seen · 54 lines · 72 tokens per session scan A 75fed7b6383c

Subscribe to this mod's changes

push-and-watch is a skill published in the GitHub repository yash-gadodia/claude-init (5 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 790 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-26.

Cloud DevOps and cloud Git and workflow Releases ai-native automation claude cli developer-tools

push-and-watch next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
push-and-watchyash-gadodia/claude-init	Skill	5	1mo ago	MIT	A	72	Claude Code
sc:deploy-remotesquadcodercom/squadcoder	Skill	12	4mo ago	MIT	D	148	Claude Code, Codex
land-and-deploygarrytan/gstack	Skill	140k	yesterday	MIT	A	14	Claude Code
rea-changelog-updatemorluto/rea	Skill	435k	today	MIT	A	33	Claude Code
codew-release-qa-sweepHmbown/CodeWhale	Skill	41k	5d ago	MIT	A	31	Claude Code, Codex
release-reviewrohitg00/ai-engineering-from-scratch	Skill	77k	yesterday	MIT	A	7	Claude Code, Codex
orchard-releaserohitg00/ai-engineering-from-scratch	Skill	77k	yesterday	MIT	A	11	Claude Code, Codex

push-and-watch