release

A production-release command that collects proof that a release is ready, passes it through the production approval gate, and deploys it. A release is a specific version of the software prepared for users.

In plain words
What is it for?
Use it to prepare a release evidence pack from a commit, verify pre-production gates, and complete the production go-live process.
Why use it?
It brings required checks and operational evidence together before deployment, including testing, rollback planning, monitoring, and relevant reliability or compliance work.

Command for Claude Code

Part of the praxis plugin — 26 skills, 12 commands, 17 agents, 6 hooks 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 commands/jeet129/praxis/release
Clone the repo
git clone --depth 1 https://github.com/jeet129/praxis

Made for: Claude Code.

Or install praxis, the plugin that ships this one along with the rest of its 26 skills, 12 commands, 17 agents, 6 hooks.

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 417 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 $0.00015 $0.00417
Opus 5 $0.00008 $0.00209
Sonnet 5 $0.00003 $0.00083
Haiku 4.5 $0.00002 $0.00042

Measured 3d ago against content hash bf9a75182300, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

release 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.

.claude/commands/release.md · 34 lines

What it actually says

Run production-release.yaml workflow for the next release.

Ask me the release SHA (or use HEAD if just stated).

Assemble the production_go_live evidence pack per governance/governance.yaml:

ALWAYS REQUIRED (Wave 3 baseline):

  1. All pre-prod gates cleared (Code Review + Security Review + QA + staging verification).
  2. DR drill recent pass (per reliability-dr cadence).
  3. Capacity sizing verified (per capacity-resource-estimation).
  4. SLO observability live (per observability — SLOs, dashboards, alerts).
  5. Rollback plan documented (per deploy-release — triggers + procedure).

CONDITIONAL (Wave 4 additions; evaluate per charter flags + change characteristics): 6. Chaos engineering pass recent — assemble if flagged in scope by governance (resilience-critical change OR multi-AZ-region); otherwise record N/A with justification. 7. Performance test soak pass — if NFR-bearing change (latency / throughput / availability). 8. Compliance evidence complete — assemble if flagged in scope by governance (any regulated regime applies); otherwise record N/A with justification. 9. Threat model updated — if architecture or trust-boundary change. 10. Supply chain attestation verified — ALWAYS (SBOM + SLSA provenance).

If has_ml or has_agentic_ai: also assemble responsible_ai_review evidence pack (5 always + 5 conditional items).

Show me the assembled pack with each item shown explicitly. I review; approve or send back.

On approval: production_deploy executes; release record archived to .project/operational/releases/; release notes generated per technical-documentation.

Common rationalizations to ignore:

  • "Small release; skip chaos." → chaos cadence is windowed (90 days); not per-release. Verify the latest pass is within window.
  • "Rollback is just revert." → must be documented per deploy-release. Trigger criteria + procedure + rehearsal date.
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 First seen · 34 lines · 15 tokens per session scan A bf9a75182300

Subscribe to this mod's changes

release is a command published in the GitHub repository jeet129/praxis (7 stars, last pushed 5d ago), licensed MIT. It adds 15 tokens to every session and 417 once invoked, about $0.0001 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.