release

A command that releases the current repository through the cibseven-devflows process, using the supplied version number. It performs a dry run first and reports whether policy approved the release or a person must approve it.

In plain words
What is it for?
Use it to run release checks, inspect release notes and gate results, approve an open gate with user permission, and report the final tag, URL, or failure details.
Why use it?
It prevents releases from skipping required setup or human approval, and avoids waiting when the policy has already approved the run.

Command

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/0langa/cibseven-devflows/release
Clone the repo
git clone --depth 1 https://github.com/0langa/cibseven-devflows
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 388 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 $0.00388
Opus 5 $0.00008 $0.00194
Sonnet 5 $0.00003 $0.00078
Haiku 4.5 $0.00002 $0.00039

Measured yesterday against content hash f49e43df39dd, 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 yesterday.

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/commands/release.md · 29 lines

What it actually says

Release version $1 of the repository in the current working directory through the cibseven-devflows release process.

Follow the release-with-devflows skill exactly:

  1. Call doctor with the repository path. Fix whatever is not ok - deploy the process or the decision with deploy_process if either is missing - before going on.
  2. Show the gates with list_gates.
  3. Start a dry run with start_release(repo_path, "$1", dry_run=true).
  4. Poll get_run and show me the gate report.
  5. Then handle whichever of the two outcomes happened:
    • No task appeared and the run has finished. The DMN policy auto-approved it. Do not wait for an approval that will never come: report policy.policy_reason so I know why nobody was asked.
    • A task is open. Show me the gate report, the drafted release_notes and notes_source, then stop and ask me before calling approve_gate. Do not approve on your own judgement. If I want different notes, tell me to edit them in the web UI form - approve_gate cannot send them.
  6. Report tag_name, release_url and state when the run ends. If the run is stuck, show the incidents from get_run and name the likely cause before suggesting retry_run.

Only start a real run (dry_run=false) if I passed --real and the dry run finished cleanly. If I did not pass --real, finish after the dry run and tell me what the real run would do.

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. yesterday First seen · 29 lines · 15 tokens per session scan A f49e43df39dd

Subscribe to this mod's changes

release is a command published in the GitHub repository 0langa/cibseven-devflows (0 stars, last pushed 9d ago), licensed Apache-2.0. It adds 15 tokens to every session and 388 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.