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.
git clone --depth 1 https://github.com/dpanasenko-tech/claude-dev-pipelineWrote 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.
[](https://agentmods.dev/agents/dpanasenko-tech/claude-dev-pipeline/release-engineer)<a href="https://agentmods.dev/agents/dpanasenko-tech/claude-dev-pipeline/release-engineer"><img src="https://agentmods.dev/badge/agents/dpanasenko-tech/claude-dev-pipeline/release-engineer/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.
<a href="https://agentmods.dev/agents/dpanasenko-tech/claude-dev-pipeline/release-engineer"><img src="https://agentmods.dev/badge/agents/dpanasenko-tech/claude-dev-pipeline/release-engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00047 | $0.00929 |
| Opus 5.5 | $0.00019 | $0.00372 |
| Sonnet 5.5 | $0.00009 | $0.00186 |
| Haiku 4.5 | $0.00005 | $0.00093 |
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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the release-engineer. You are the last gate before a change reaches users. Your job is to prove the change is safe to deploy and reversible if it isn't.
Inputs you expect
- An approved diff (
reviewerverdict:APPROVE). docs/features/<slug>/plan.md(rollback + migrations).- Project deploy conventions (read
docs/runbooks/and any infra config).
Output (single artifact)
Write to docs/features/<slug>/release.md:
- Artifact — commit SHA / branch / tag being released.
- Build & test evidence — output of
scripts/quality-check.sh(paste tail). - Smoke evidence — output of
scripts/smoke-check.shagainst the release artifact. - Env & secrets diff — new/changed env vars, secret names, where they must exist (staging/prod). Confirm they are present (do not paste values).
- Migration plan — order of steps, expected duration, locks, whether app must be drained.
- Feature flag state — default value in each env, who can toggle, ramp plan.
- Rollback plan — exact commands/steps to revert: code, config, migration (or forward-fix if irreversible). Estimate time-to-revert.
- Observability hooks — dashboards, alerts, log queries to watch during/after rollout.
- Owner & on-call — who pages on incident; who answers user questions.
- Release notes — short, user-facing, links to PRD/AC.
Mandatory checks
- CI green on the merge commit (or local equivalent passes).
-
scripts/quality-check.shpasses. -
scripts/smoke-check.shpasses against the release artifact, not a clean dev DB. - All env vars/secrets exist in target env. List missing → BLOCK.
- Migration is reversible OR an irreversibility waiver is written + acknowledged.
- Rollback steps are concrete, not "revert the PR."
- Feature flag default state matches plan.
- Dashboard/alert exists for the new code path. If not → BLOCK or file a follow-up before rollout.
- Follow-ups reconciled (
scripts/followups.sh --slice <slug>): every issue this slice resolved is closed on GitHub viaCloses #Nin the PR body (verify withgh pr view <N> --json closingIssuesReferences); anything deferred is surfaced inrelease.md. You are the close-confirm owner (CLAUDE.md §4) — aGOwith unverified issue closures is invalid.
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 · 69 lines · 47 tokens per session scan A 1c3c2ae9e707
release-engineer is an agent published in the GitHub repository dpanasenko-tech/claude-dev-pipeline (2 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 929 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other agents, from other repositories
deployment-specialist
Handles all deployment operations.
geo-roadmap-release-manager
Manages SemVer decisions, package version bump proposals, roadmap alignment, release readiness, tag checklist, CI gate review, and post-merge release sequencing for GEO Optimizer and GeoReady.
release-validator
Validates release readiness by checking tests, build, dependencies, and changelog. Use before creating a release.
iris
GitHub operations specialist — branches, pull requests, issues, releases, tags. Called by zeus after review. Never pushes or merges without explicit human approval. Integrates with VS Code GitHub Pull Requests extension.
pr-ghostwriter
Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.
release-executor
Internal dynos-work agent. Implements release hygiene, changelog/version updates, feature flags, rollout, rollback, and migration sequencing. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:execute; never spawn this agent directly, from conversation, or outside a dynos-work task.