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.
npx skills add darellchua2/opencode-config-template --skill git-branch-workflow-setup-skillgit clone --depth 1 https://github.com/darellchua2/opencode-config-templateWrote 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.
[](https://agentmods.dev/skills/darellchua2/opencode-config-template/git-branch-workflow-setup-skill)<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/git-branch-workflow-setup-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/git-branch-workflow-setup-skill/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.
<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/git-branch-workflow-setup-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/git-branch-workflow-setup-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00045 | $0.02346 |
| Opus 5.5 | $0.00018 | $0.00938 |
| Sonnet 5.5 | $0.00009 | $0.00469 |
| Haiku 4.5 | $0.00005 | $0.00235 |
Grade A, and why
git-branch-workflow-setup-skill 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 28d 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.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What I do
I am an orchestration skill — I do NOT execute branch setup myself. I provide the primary agent with:
- Detection logic — when to offer branch-workflow setup
- Question tool spec — the exact prompt to present to the user
- Option matrix — what the user can configure (as cross-references)
- Delegation spec — the typed payload to pass to
repo-ops-specialist-subagent
The primary agent loads me, extracts these parameters, prompts the user, then delegates execution to repo-ops-specialist-subagent (which has bash: allow and the execution skills).
When to use me
Invoke me when any subagent returns NEEDS_GIT_BRANCH_SETUP: true in its Return Contract. This signal indicates a project was just scaffolded (or a ticket workflow completed) and may benefit from a release branch structure.
Governance
Content Rule: This skill MUST contain ZERO inline YAML templates, ZERO bash scripts, and ZERO label hex colors. All execution logic and conventions are cross-references to the governing skills. This rule is auditable — if any inline template/script/hex is found, it is a defect.
This skill defers to:
| Aspect | Governing Skill | Section Reference |
|---|---|---|
| Execution (scripts, workflows, onboarding) | version-bump-standard-skill |
§Onboarding Checklist, §Templates & Scripts, §Workflow Templates, §Branch Flow |
| Tag formats & label conventions | semantic-release-convention-skill |
§5. Release Tag Convention, §Branch-Aware Tag Mapping, §3. PR Label Rules |
| Changelog generation | semantic-release-convention-skill |
§6. GitHub Actions Requirements |
Why deferral (not duplication): If governance changes (e.g., tag format, label colors), only the governing skill needs updating. This skill never needs to change for convention updates.
Detection Logic
Before offering branch-workflow setup, check for existing release tooling. Offer setup ONLY when ALL of the following are absent from the target project:
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.
- 28d ago Changed cae94d45ea7f
- 1mo ago First seen · 189 lines · 45 tokens per session scan A 21a3a772fe7c
git-branch-workflow-setup-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed 28d ago), licensed Apache-2.0. It adds 45 tokens to every session and 2,346 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
git-ship
An automated Git release workflow that takes code changes through a branch, commit, pull request, review checks, squash merge, and return to the main branch. A pull request is a request to review and merge changes into a shared branch.
jig-github-sync
Use when synchronizing this repository's GitHub setup: main/develop branches, optional branch protection, and the managed local guards (the git pre-push hook plus the native Codex and Antigravity push hooks), including guard cleanup before uninstalling jig. Do not use for creating a release.
jig-version-rubric
Use when creating, reviewing, or re-setting this repository's version grading rubric at .jig/versioning.md: adopt the jig default human-intervention rubric, write a project-specific one, edit one grade, or reset to the default. Owns the rubric file; never runs a release.
jig-develop-task-flow
Use for ordinary implementation tasks in a repository that has adopted the jig develop/main model: start from develop, create a feature/fix/chore branch, complete changes and tests, squash-merge back into develop locally, and push develop. No pull requests. Execution scope comes from the current request and explicitly…
jig-github-release
Use when releasing this repository from the CLI by promoting develop to main with a fast-forward push, grading the release as patch/minor/major by what installed projects actually pay, computing the next version from the latest tag, and publishing a GitHub release with agent-written notes. No release PR, no…
jig-hotfix-flow
Use when a released defect on main must ship before the work already sitting on develop. Branches from main, lands one squashed commit on main through the guard-allowed hotfix push, tags and publishes, then merges main back into develop so the next release still fast-forwards.