publish

publish is a skill for Claude Code, Codex from asysta-act/agent-flow. It costs 20 tokens per session (4,303 once invoked), scanned A, original, MIT.

A publishing workflow that opens a pull request (a proposed code change for review) and may update the related issue in the issue tracker.

In plain words
What is it for?
Use it to publish finished work from a branch, create a pull request, and optionally move its linked issue to the next state.
Why use it?
It removes the repeated steps of creating the pull request and changing the issue status. It chooses the publishing mode from the current Git branch name.

Skill for Claude CodeCodex

Part of the agent-flow plugin — 17 skills, 17 agents shipped together

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 skills/asysta-act/agent-flow/publish
Any agent
npx skills add asysta-act/agent-flow --skill publish
Clone the repo
git clone --depth 1 https://github.com/asysta-act/agent-flow

Made for: Claude Code, Codex.

Or install agent-flow, the plugin that ships this one along with the rest of its 17 skills, 17 agents.

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.

agentmods badge for publish

README.md
[![agentmods](https://agentmods.dev/badge/skills/asysta-act/agent-flow/publish.svg)](https://agentmods.dev/skills/asysta-act/agent-flow/publish)
Your own site
<a href="https://agentmods.dev/skills/asysta-act/agent-flow/publish"><img src="https://agentmods.dev/badge/skills/asysta-act/agent-flow/publish.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,303 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00020 $0.04303
Opus 5 $0.00010 $0.02152
Sonnet 5 $0.00004 $0.00861
Haiku 4.5 $0.00002 $0.00430

Measured 5d ago against content hash c672d0dd8359, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

publish scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl --proto "=http,https" --max-time 5 --retry 0 -X POST -H "Content-Type: application/json" \
skills/publish/SKILL.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Publish

Publish current work: PR + (conditional) issue tracker state change. Read Automation Config from CLAUDE.md.

/publish auto-detects the publishing mode from the current branch name and the Automation Config Source Control → Branch naming template. There are three success modes (full-publish, pr-only-no-id, pr-only-404) and one failure mode (FAIL). No flags. No new config keys. The "PR-only with valid tracker reference" use case is expressed by renaming the branch to one that does not match the configured Branch naming prefix (e.g., chore/refactor-foo instead of fix/PROJ-123-foo).

Operator note (interactive-only): /publish is interactive-only — it requires user confirmation flows in agent prose and may FAIL in environments without an MCP server configured (CI / cron). For headless / batch publishing, use /agent-flow:autopilot.

Steps

Step 0 — Branch parse (NEW pre-pre-flight)

This step runs BEFORE the MCP pre-flight. It determines whether the tracker is needed at all.

0a. Resolve the current branch name.

branch_name=$(git branch --show-current)

If branch_name is empty, the working tree is in a detached HEAD state. There is no active branch to push or to use as the PR source, so /publish cannot proceed. FAIL with a single-line INFO message and EXIT non-zero:

[agent-flow][INFO] Cannot determine branch (detached HEAD). /publish requires an active branch.

This is a pre-flight environment check — NOT a tracker-down failure — so it does NOT use the [agent-flow] 🔴 Pipeline Block template. No tracker comment is posted. No webhook event is fired. (Detached HEAD is treated as FAIL — exit non-zero — NOT as pr-only-no-id, because there is no branch to push or use as PR source.)

0b. Read Source Control → Branch naming from Automation Config.

The template uses {issue-id} (and optionally {description}) as placeholders — for example fix/{issue-id}-{description} or feature/{issue-id} (per docs/reference/automation-config.md Branch naming row).

Read the full file on GitHub · 327 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. 5d ago First seen · 327 lines · 20 tokens per session scan A c672d0dd8359

Subscribe to this mod's changes

publish is a skill published in the GitHub repository asysta-act/agent-flow (12 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 4,303 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

agent-framework-py-release

Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…

microsoft/agent-framework · 103 tokens

release

Cut a FastMCP release end to end. Use when the maintainer says "cut a release", "prep a patch", "ship 4.x.y", or asks what a release would contain. Covers the notes preview, the title pun, the docs changelog PR that must land before the tag, the tag itself, the publish fan-out, and verifying gofastmcp.com actually…

PrefectHQ/fastmcp · 83 tokens

release-notes

Draft short release notes from a list of changes. Use when the user asks for changelogs, release notes, or a concise product update.

cloudflare/agents · 33 tokens

changelog

Generate or update the CHANGELOG.md for a new release version. Use when the user says "generate changelog", "update changelog", "write release notes", or asks to prepare a changelog for a version like "changelog for 0.5.3".

entireio/cli · 58 tokens

release-validation

Use this skill when validating a MeshLLM release candidate or current HEAD against the last GitHub release, assembling the canonical feature/fix/modification inventory, testing locally built release bundles on user-approved real hosts and private meshes, deciding release readiness, or producing a formal…

Mesh-LLM/mesh-llm · 62 tokens

changelog

Turn a range of commits or merged PRs into a changelog entry grouped by change type. Use when the user asks for release notes, a changelog, or "what changed" between two points.

omnigent-ai/omnigent · 44 tokens