safe-deployment

safe-deployment is a skill for Claude Code, Codex from aethrox/doctrine. It costs 93 tokens per session (1,074 once invoked), scanned A, original, MIT.

A release-planning method for shipping risky software changes in reversible stages. It separates deploying code to production from releasing its behaviour to users.

In plain words
What is it for?
Use it to decide on feature flags, internal or percentage-based rollouts, health criteria, rollback triggers, and cleanup deadlines for temporary flags.
Why use it?
It limits the number of users affected by a problem and makes rollback a planned action instead of an emergency decision.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the doctrine plugin — 33 skills shipped together

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.

agentmods
npx agentmods add skills/aethrox/doctrine/safe-deployment
Any agent
npx skills add aethrox/doctrine --skill safe-deployment
Clone the repo
git clone --depth 1 https://github.com/aethrox/doctrine

Made for: Claude Code, Codex.

Or install doctrine, the plugin that ships this one along with the rest of its 33 skills.

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 safe-deployment

README.md
[![agentmods](https://agentmods.dev/badge/skills/aethrox/doctrine/safe-deployment.svg)](https://agentmods.dev/skills/aethrox/doctrine/safe-deployment)
Your own site
<a href="https://agentmods.dev/skills/aethrox/doctrine/safe-deployment"><img src="https://agentmods.dev/badge/skills/aethrox/doctrine/safe-deployment.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,074 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00093 $0.01074
Opus 5 $0.00046 $0.00537
Sonnet 5 $0.00019 $0.00215
Haiku 4.5 $0.00009 $0.00107

Measured 6d ago against content hash 7e0f19316a29, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

safe-deployment 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.

skills/safe-deployment/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Safe Deployment

Every deploy is reversible before it becomes visible. That means treating "code reaches production" and "users see the new behaviour" as two separate, independently controllable events, rolling exposure out in steps instead of all at once, and deciding what "unhealthy, roll back" means while writing the deploy plan, not while paged at 3am reading dashboards for the first time.

Phase 1: Decouple deploy from release

Before choosing a rollout strategy, decide whether this change needs a feature flag:

  • If the change is risky, user-visible, or its blast radius is unclear; put it behind a flag. The code ships to production dark (compiled in, disabled), and "release" becomes flipping a config value, not another deploy.
  • A flagged change can be enabled for an internal allowlist first, then a percentage of traffic, then everyone; all without a redeploy, and all instantly reversible by flipping the flag back off.
  • Flags accumulate cost (branches to test, config to reason about); remove a flag once the change has fully rolled out and stabilized; a flag left in forever is dead code with a stated deadline that got ignored.

Phase 2: Choose the rollout strategy

Strategy How it works Reach for it when
Rolling replace instances a few at a time, old and new versions serve traffic simultaneously during the rollout default for stateless services with no schema change; simplest, no extra infrastructure
Canary route a small percentage (often 1–5%) of real traffic to the new version, watch its signals, then widen the change is risky enough to want real-traffic validation before full exposure, and the service has per-version metrics to compare
Blue-green two full identical environments, traffic cut over from old to new all at once, old kept warm for instant rollback the change can't safely run two versions concurrently (e.g. a coordinated multi-service release), and instant full rollback matters more than gradual exposure

Read the full file on GitHub · 51 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 51 lines · 93 tokens per session scan A 7e0f19316a29

Subscribe to this mod's changes

safe-deployment is a skill published in the GitHub repository aethrox/doctrine (18 stars, last pushed 24d ago), licensed MIT. It adds 93 tokens to every session and 1,074 once invoked, about $0.0005 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 2026-08-30.

Related

Other skills, from other repositories

release-openspec

Use this skill when releasing OpenSpec: audit merged work and changeset coverage, decide whether a catch-up changeset PR is needed, prepare or resume the Changesets Version Packages PR, cut a beta or stable release, verify publishing, and polish GitHub release notes. Also use when asked whether an open release PR is…

Fission-AI/OpenSpec · 88 tokens

changelog-writer

Write changelogs for Bifrost releases. Reads git history, bumps module versions following the core→framework→plugins→transport hierarchy, writes transports/changelog.md (enterprise-style) and per-module changelog.md files, and updates version files. Invoked with /changelog-writer or /changelog-writer .

maximhq/bifrost · 73 tokens

split-commit-into-stack

Split one oversized commit or branch into a stack of independently reviewable Graphite (gt) PRs - deciding what genuinely separates, what is atomic and must stay whole, and proving each lower PR builds and passes without the ones above it. Use when asked to "split this PR", "this commit is too big", "break this into a…

maximhq/bifrost · 96 tokens

release-checklist

Pre-release safety audit for the Bifrost repo. Scans database migrations changed in a release for high-scale deadlock / lock-contention risks and for work that blocks application boot time, then produces a pass/warn/fail report with a concrete remediation plan. Invoked with /release-checklist [git-ref-range]. Built to…

maximhq/bifrost · 82 tokens

xcodebuildmcp-docs-release-review

Use when reviewing XcodeBuildMCP documentation, CLI command references, website manifest generation, changelog, release notes, and release script changes.

getsentry/XcodeBuildMCP · 39 tokens

portainer-mcp-release

How to cut a portainer-mcp release that bumps the embedded Portainer OpenAPI spec to a new Portainer minor (e.g. 2.41.x → 2.42.x). Walks through finding the upstream patch target, regenerating the spec, recounting ops/tags per profile, refreshing the orphan-tag inventory, bumping version pins across the README and…

portainer/portainer-mcp · 186 tokens