deployment-safety

deployment-safety is a skill for Claude Code from juan294/cc-rpi. It costs 35 tokens per session (1,022 once invoked), scanned A, original, MIT.

A set of rules for safer production releases and repository maintenance, including rollback planning, dependency updates, CI usage, upgrades, and GitHub settings.

In plain words
What is it for?
Use it to batch dependency changes, choose the correct branch and release path, justify CI runs, verify framework upgrades, and prepare fallback monitoring.
Why use it?
It reduces accidental production deployments, repeated CI runs, difficult dependency merges, and upgrades that have not been properly checked.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the cc-rpi plugin — 36 skills, 19 commands, 2 hooks shipped together

Good fit Use it to batch dependency changes, choose the correct branch and release path, justify CI runs, verify framework upgrades, and prepare fallback monitoring.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/juan294/cc-rpi/deployment-safety
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 juan294/cc-rpi --skill deployment-safety
Clone the repo
git clone --depth 1 https://github.com/juan294/cc-rpi

Made for: Claude Code.

Or install cc-rpi, the plugin that ships this one along with the rest of its 36 skills, 19 commands, 2 hooks.

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 deployment-safety

README.md
[![agentmods](https://agentmods.dev/badge/skills/juan294/cc-rpi/deployment-safety/github.svg)](https://agentmods.dev/skills/juan294/cc-rpi/deployment-safety)
Your own site
<a href="https://agentmods.dev/skills/juan294/cc-rpi/deployment-safety"><img src="https://agentmods.dev/badge/skills/juan294/cc-rpi/deployment-safety/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 deployment-safety

Your own site · 80×15
<a href="https://agentmods.dev/skills/juan294/cc-rpi/deployment-safety"><img src="https://agentmods.dev/badge/skills/juan294/cc-rpi/deployment-safety.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,022 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.01022
Opus 5 $0.00017 $0.00511
Sonnet 5 $0.00007 $0.00204
Haiku 4.5 $0.00003 $0.00102

Measured 3d ago against content hash b0f6b826b7c2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

deployment-safety 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 3d 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.

generated/claude/skills/deployment-safety/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deployment Safety

Merging to Main

Read the actual deployment topology: main may be canonical source, production, or both. A merge/push that deploys production requires explicit production authorization. A request to clean up dependency PRs is not release authorization.

Keep working branches and worktrees local. Finish applicable tests, coverage, typechecks, lint, build and deployment preflight locally, resolve failures, and integrate completed work locally into the documented integration branch. Inspect workflow and deployment triggers before the single authorized push of that completed branch. Never create Vercel Preview deployments or publish working branches/PRs for experimentation. If an integration push would create a Preview, stop before pushing and use only a documented, non-destructive bypass. Production publication remains separately and explicitly authorized. Read-only inspection of existing runs and deployments is allowed.

Dependency Batching

Inspect existing dependency PRs read-only. Apply the relevant updates together on one local task-owned branch based on the documented integration branch:

git switch -c chore/dependency-updates <integration-branch>
# Apply reviewed updates and run the complete applicable local gate.

Integrate the verified result locally. Never merge dependency PRs one-by-one, push fixes to their branches, request remote rebases, or create a batch PR as a debugging loop. Closing/commenting on existing PRs needs authorization.

CI Cost Awareness

Run tests, coverage, typechecks, lint, build and deployment preflight locally when applicable. Use && or explicit status aggregation so an early failing check cannot be hidden by later success. Inspect all trigger types before the single authorized integration push, including auxiliary workflows and report publication. Existing logs and statuses can be inspected without triggering runs.

Framework Upgrades

A green build alone does not establish runtime compatibility. Exercise local runtime smoke tests, packaging and platform preflight, and inspect existing platform logs/configuration. Never create a Vercel Preview. Record any remaining platform-only uncertainty in the candidate's release review; do not claim local tests prove an unexercised hosted runtime works.

Read the full file on GitHub · 134 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.

  1. 3d ago Changed · -36 lines b0f6b826b7c2
  2. 9d ago First seen · 170 lines · 35 tokens per session scan A e39b3713c4d8

Subscribe to this mod's changes

deployment-safety is a skill published in the GitHub repository juan294/cc-rpi (5 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 1,022 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 2026-08-31.

Related

Other skills, from other repositories

changelog

Turn a range of commits or merged PRs into a changelog entry grouped by change type. Use when the user asks for release notes, a changelog, or "what changed" between two points.

omnigent-ai/omnigent · 44 tokens

taiyi-integration

A project workflow skill for closing a TaiyiForge change and recording it in a CHANGELOG.md file. It checks review results, tests, and the state of the working tree before archiving the change.

Dong90/oh-my-taiyiforge · 27 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

release-engineering

Plan and verify software releases with versioning, changelogs, release branches, feature flags, canaries, migration gates, rollback, deployment checks, and release readiness. Use when preparing a release, shipping a risky PR, coordinating app/backend/database rollout, recovering from a bad deploy, or defining release…

majiayu000/spellbook · 69 tokens

release

Guide through the Cortex TMS release process — version bump, changelog, sync, tag, publish. Every step requires user approval.

cortex-tms/cortex-tms · 29 tokens

autoship

Runs a changesets npm release through the version PR, CI publish, and registry verification. Use when asked to "release this package", "autoship", "merge Version Packages", or diagnose a release that did not publish. For feature PRs use pr-creator or pr-babysitter.

mblode/agent-skills · 63 tokens