release

A release command for a project called Fellowship. It coordinates version selection, documentation checks, changelog updates, tagging, pushing, and marketplace updates.

In plain words
What is it for?
Use it to prepare and publish a release, choose a version from recent changes, validate the docs, and update the related repositories.
Why use it?
It brings the release steps into one guided process and checks documentation before publishing a new version.

Command for Claude Code

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/justinjdev/fellowship/release
Clone the repo
git clone --depth 1 https://github.com/justinjdev/fellowship

Made for: Claude Code.

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 698 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 $0.00025 $0.00698
Opus 5 $0.00013 $0.00349
Sonnet 5 $0.00005 $0.00140
Haiku 4.5 $0.00003 $0.00070

Measured yesterday against content hash af12c3020a0e, 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.

.claude/commands/release.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release

Automates the full release process for fellowship.

Step 1: Determine Version

Read the current version from .claude-plugin/plugin.json.

Analyze commits since the last tag (git log $(git describe --tags --abbrev=0)..HEAD --oneline --no-merges) and suggest a version based on conventional commit types:

  • feat: → minor bump
  • fix: only → patch bump
  • Breaking changes → minor bump (pre-1.0: major)

Present the suggestion and ask the user to confirm or override:

Current version: X.Y.Z
Commits since last tag: N

Suggested next version: X.Y.Z (reason)

Enter version to release (or confirm suggested):

Use AskUserQuestion with the suggested version as default and a free-text option.

Step 2: Validate Docs

Invoke the validate-docs skill using the Skill tool. Review any flagged issues and ask the user whether to fix them now or proceed anyway.

If fixing: make the updates before continuing. Renaming an "Unreleased" changelog section to the new version is handled in Step 3 below — skip that specific fix here.

If proceeding with known issues: record which checks had findings. These will be surfaced as warnings in the Step 6 summary instead of checkmarks.

Step 3: Bump Version

Update the version string in .claude-plugin/plugin.json.

If the site changelog has an "Unreleased" section, rename it to the new version with the standard format:

<section class="version" id="v{version-dashed}">
    <h2 class="version-heading"><a href="{base}/changelog#v{version-dashed}">v{version}</a></h2>

Also update the HTML comment above it from <!-- unreleased --> to <!-- v{version} -->.

Step 4: Commit, Tag, Push

git add -A
git commit -m "chore: release v{version}"
git tag v{version}
git push && git push --tags

Verify the push succeeded. If it fails, stop and report.

Step 5: Update Marketplace

Read ~/git/claude-plugins/.claude-plugin/marketplace.json. Update the fellowship plugin's version field to the new version.

Read the full file on GitHub · 92 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.

  1. yesterday First seen · 92 lines · 25 tokens per session scan A af12c3020a0e

Subscribe to this mod's changes

release is a command published in the GitHub repository justinjdev/fellowship (5 stars, last pushed 18d ago), licensed Apache-2.0. It adds 25 tokens to every session and 698 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.

Related

Other commands, from other repositories

auto-mode

Idea-to-running-code lifecycle orchestration. 10-phase pipeline with 5 hard decision gates, wave-based parallelism, and STATE.json resumability. Composes /deep-research, /auto-swarm-nth, /production-upgrade, /security-audit, and /ship into a single end-to-end flow.

ShaheerKhawaja/ProductionOS · 68 tokens

max-research

Nuclear-scale autonomous research — deploys 500-1000 agents in ONE massive simultaneous wave for exhaustive topic saturation. Deep-research methodology × auto-swarm scale = maximum parallel intelligence. WARNING: Extreme resource consumption.

ShaheerKhawaja/ProductionOS · 48 tokens

omni-plan

ProductionOS flagship — 13-step orchestrative pipeline with tri-tiered evaluation, recursive convergence, CEO/Eng/Design review chain, CLEAR framework evaluation, multi-model judge tribunal, and autonomous PIVOT/REFINE/PROCEED decisions. Targets 100% production-ready output.

ShaheerKhawaja/ProductionOS · 62 tokens

auto-swarm-nth

Nth-iteration agent swarm — spawns parallel agent waves, evaluates strictly per wave, re-swarms gaps until 100% coverage and 10/10 quality. Can invoke any ProductionOS skill or command within waves.

ShaheerKhawaja/ProductionOS · 51 tokens

frontend-upgrade

Full-stack frontend upgrade pipeline — fuses /production-upgrade iterative audit with /plan-ceo-review vision and /plan-eng-review rigor. Deploys parallel auto-swarm agents for iterative audit and execution. Enriched with /deep-research for competitive parity.

ShaheerKhawaja/ProductionOS · 56 tokens

omni-plan-nth

Nth-iteration omni-plan — recursive orchestration that chains ALL ProductionOS skills and agents, evaluates strictly per iteration, and loops until 10/10 is achieved. Each iteration can invoke any command or skill in the system.

ShaheerKhawaja/ProductionOS · 51 tokens