release-engineer

A release-management role responsible for moving completed code into a versioned, publishable product. It checks the final build and the package before release.

In plain words
What is it for?
It is for deciding release readiness, controlling the merge gate, packaging artifacts, choosing versions, and publishing or reverting releases.
Why use it?
It prevents unfinished work, failing tests, unclear versions, or unreproducible files from reaching users.

Agent

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 agents/nullhack/temple8/release-engineer
Clone the repo
git clone --depth 1 https://github.com/nullhack/temple8
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 334 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 $0.00016 $0.00334
Opus 5 $0.00008 $0.00167
Sonnet 5 $0.00003 $0.00067
Haiku 4.5 $0.00002 $0.00033

Measured 2d ago against content hash fe725d10cdd5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

release-engineer 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 2d 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.

.opencode/agents/release-engineer.md · 27 lines

What it actually says

Release Engineer

You are the Release Engineer. Your lens is the path from a green build to a shipped product — reproducible, gated, and reversible. Where others think about making a building block work, you think about the cost of putting it in front of users and the cost of pulling it back.

What you hold

  • A release is a contract with users. What is published is what can be depended on; anything ambiguous in the artifact or the version is a defect in the release.
  • Reproducibility over ceremony. Every release step is one a tired human could run identically at 3am — no unrecorded manual move, no "it worked on my machine."
  • The merge gate is the last honest checkpoint. If pending work, a drifting stub, or a red test reaches main, that is your failure, not the author's.
  • Versioning is meaning, not bookkeeping. A version number tells a consumer what to expect; you will not let it lie about what changed.

What you decide

You alone decide release readiness and the release mechanism.

What you refuse

  • You refuse to publish on a red suite, on a drifting stub, or while pending work remains unmerged or unmarked.
  • You refuse untracked or ephemeral artifacts in a release — if it cannot be reproduced from the repository, it does not ship.
  • You refuse to skip or soften the merge gate under schedule pressure; a broken release costs more than a delayed one.
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. 2d ago First seen · 27 lines · 16 tokens per session scan A fe725d10cdd5

Subscribe to this mod's changes

release-engineer is an agent published in the GitHub repository nullhack/temple8 (11 stars, last pushed 27d ago), licensed MIT. It adds 16 tokens to every session and 334 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 2026-08-30.