What is release-with-devflows?

A release workflow for repositories containing a devflows.yaml file. It runs release steps through a local process engine, with a decision table determining whether human approval is needed.

It is for checking a repository, creating release notes, deciding on approval, tagging the release, and publishing it.

It provides a defined path from release checks to publishing and can undo the tag if publishing fails. It also stops when the repository configuration cannot be parsed.

release-with-devflows — Skill for Claude Code by 0langa

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 0langa/cibseven-devflows --skill release-with-devflows

Clone the repo

git clone --depth 1 https://github.com/0langa/cibseven-devflows

Made for: Claude Code.

Or install cibseven-devflows, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 MCP server.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/0langa/cibseven-devflows/release-with-devflows/github.svg)](https://agentmods.dev/skills/0langa/cibseven-devflows/release-with-devflows)

Your own site

<a href="https://agentmods.dev/skills/0langa/cibseven-devflows/release-with-devflows"><img src="https://agentmods.dev/badge/skills/0langa/cibseven-devflows/release-with-devflows/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/0langa/cibseven-devflows/release-with-devflows"><img src="https://agentmods.dev/badge/skills/0langa/cibseven-devflows/release-with-devflows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,463 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.

Model	Per session	Once invoked
Fable 5.1	$0.00086	$0.01463
Opus 5.5	$0.00034	$0.00585
Sonnet 5.5	$0.00017	$0.00293
Haiku 4.5	$0.00009	$0.00146

Measured 1mo ago against content hash dd54fd53666f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

release-with-devflows 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.

plugin/skills/release-with-devflows/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Releasing through cibseven-devflows

The release runs as a BPMN process on a local CIB seven engine. The engine owns the state and the history; the worker on this machine runs the commands; a decision table decides whether a human is asked at all.

The process is:

gates -> draft release notes -> decide policy (DMN) -> approval required?
    no  -> tag -> publish
    yes -> human approval (with a timer) -> approved? -> tag -> publish

If publishing fails after the tag was created, the process compensates and deletes the tag again.

Before you start

Call doctor(repo_path). One call reports the engine, whether the devflows-release process and the release-policy decision are deployed, and whether the repository's devflows.yaml parses. Read the checks list and fix what is not ok:
- engine not reachable: docker compose -f engine/docker-compose.yml up -d, wait ~30 seconds.
- process or decision not deployed: call deploy_process.
- devflows.yaml fails to parse: the repository cannot be released this way. Stop. Only if doctor is unavailable, fall back to engine_status plus list_processes.
The worker. There is no tool for this. If a run makes no progress, the worker is almost always the reason: the user must run uv run devflows-worker in a second terminal.

The order to call the tools

list_gates(repo_path) - show the user what is about to run.
start_release(repo_path, version, dry_run=true) - always rehearse first. Report the process instance id and the link to the run in the web UI.
get_run(process_instance_id) - poll. Show the user the gates list, not the raw variables. Then read the result carefully, because there are two different outcomes. See below.
get_run again at the end to report tag_name, release_url and state.
Only when the dry run finished cleanly, offer the real run: start_release(repo_path, version, dry_run=false).

A release may not stop for a human at all

Read the full file on GitHub · 118 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.

1mo ago First seen · 118 lines · 86 tokens per session scan A dd54fd53666f

Subscribe to this mod's changes

release-with-devflows is a skill published in the GitHub repository 0langa/cibseven-devflows (0 stars, last pushed 6d ago), licensed Apache-2.0. It adds 86 tokens to every session and 1,463 once invoked, about $0.0003 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.

Git and workflow Releases

release-announcement

Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.

paperclipai/paperclip · 42 tokens

release

Fully automate a release with version-bump and childhood.

thedotmack/claude-mem · 13 tokens

release-notes

Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.

phuryn/pm-skills · 57 tokens

release-with-devflows