agentics-beyond-code: Skill for Codex

.github/skills/github-workflow-builder/SKILL.md

github-workflow-builder is a skill for Codex from chrizbo/agentics-beyond-code. It costs 154 tokens per session (1,737 once invoked), scanned A, original, MIT.

A setup builder for GitHub Agentic Workflows, repository-based automations that work with GitHub Issues, Projects, and Discussions.

In plain words
What is it for?
Use it to create or adapt workflows, policies, issue templates, labels, project boards, and related repository documents.
Why use it?
It turns a team's working process into the supporting files and GitHub configuration needed to run it, rather than leaving the process as informal instructions.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

This is chrizbo/agentics-beyond-code's own configuration. It tells Codex how to work on agentics-beyond-code itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentics-beyond-code configures →

Reuse

Borrowing it

Nothing to install: this file belongs to chrizbo/agentics-beyond-code. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/chrizbo/agentics-beyond-code/main/.github/skills/github-workflow-builder/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/chrizbo/agentics-beyond-code

Made for: Codex.

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 github-workflow-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/chrizbo/agentics-beyond-code/github-workflow-builder/github.svg)](https://agentmods.dev/skills/chrizbo/agentics-beyond-code/github-workflow-builder)
Your own site
<a href="https://agentmods.dev/skills/chrizbo/agentics-beyond-code/github-workflow-builder"><img src="https://agentmods.dev/badge/skills/chrizbo/agentics-beyond-code/github-workflow-builder/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.

agentmods 80×15 button for github-workflow-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/chrizbo/agentics-beyond-code/github-workflow-builder"><img src="https://agentmods.dev/badge/skills/chrizbo/agentics-beyond-code/github-workflow-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,737 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00154 $0.01737
Opus 5.5 $0.00062 $0.00695
Sonnet 5.5 $0.00031 $0.00347
Haiku 4.5 $0.00015 $0.00174

Measured 18d ago against content hash 465e6519d17a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

github-workflow-builder 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 18d 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.

.github/skills/github-workflow-builder/SKILL.md · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Workflow Builder

This skill implements an Agentics Beyond Code design on GitHub: selected GitHub Agentic Workflows, supporting documents, folder structure, policies, issue templates, labels, project boards, and adoption steps. It is the GitHub builder alongside claude-native-workflow-builder and productboard-agent-builder.

Installed plugin context

When installed as a plugin, resolve bundled repository paths from the package root (three directories above this SKILL.md), not the user's working folder. Resolve references/, prompts/, and assets/ relative to this skill folder. The package is reference material; create deliverables in the user's selected workspace and assess the user's artifacts, never the bundled demo data. For an explicitly supplied source checkout, read that checkout's current files. A checkout is the current working directory when it is this repository, or a path the user gives. Never search the file system for one (no find /, mdfind, or home-directory scans): that is slow and triggers operating-system privacy prompts. Use the pinned source index instead. The directory plugin does not bundle runtime workflows, helper scripts, or demo data. Before using a repository path outside this skill, read docs/source-access.md at the package root. It explains how to locate and fetch specific files from the recorded public source revision. If source access is unavailable, request a checkout or the relevant files; do not invent a workflow or say it was read. Blank templates and assessment references work offline. Installing these skills does not connect services, install gh/gh aw, or activate workflows or scheduled tasks. Check available tools before using them.

Core workflow

  1. Start from a design. If the user or agentic-workflow-planner already produced one, use it. If not, and the user can't name the workflows they want, run the planner's Design mode (../agentic-workflow-planner/references/design.md) first, keeping it short. Confirm that GitHub really is the team's home; if it isn't, suggest claude-native-workflow-builder or productboard-agent-builder.
  2. Confirm the GitHub-specific choices:
    • target repo and whether it already has content
    • whether they want GitHub Projects, labels, and issue templates set up
    • tolerance for automation creating issues, comments, or PRs
    • which AI provider the org already uses. Set every copied workflow's engine: to match. If the org has GitHub Copilot, suggest the Copilot engine: it needs no separate API key. Keep Codex only if they use OpenAI. Check current gh-aw engine docs rather than assuming names.
  3. Read prompts/scaffold-github-setup.md for the scaffolding procedure.
  4. Inspect this repo for reusable source material before creating anything:
    • .github/workflows/*.md
    • .github/policies/*.md
    • .github/ISSUE_TEMPLATE/*.yml
    • docs/how-it-works.md
  5. Create or update a concrete setup in the target repo:
    • blank docs/strategy.md and docs/how-we-work.md
    • folders for decisions/, transcripts/, .github/policies/, .github/workflows/, and .github/ISSUE_TEMPLATE/
    • optional project board plan, label taxonomy, and generic issue templates
    • copied or adapted workflow .md files from Agentics Beyond Code
    • copied or adapted policy and issue-template files when the workflow needs them
  6. For gh-aw authoring details (frontmatter, triggers, safe outputs, debugging), use the agentic-workflows skill when it is available: it is present in a checkout of this repo and in repos set up with gh aw init. Otherwise, fetch the instructions it routes to directly from github/gh-aw, starting with .github/aw/create-agentic-workflow.md. The Claude plugin does not include agentic-workflows.
  7. Validate the setup with gh aw compile --strict when gh-aw is available.

Read the full file on GitHub · 141 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. 18d ago Changed · +16 lines 465e6519d17a
  2. 25d ago First seen · 125 lines · 154 tokens per session scan A 2b1e1472ba69

Subscribe to this mod's changes

github-workflow-builder is a skill published in the GitHub repository chrizbo/agentics-beyond-code (34 stars, last pushed 4d ago), licensed MIT. It adds 154 tokens to every session and 1,737 once invoked, about $0.0006 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 2026-09-30.