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 TheSmuks/ai-project-template --skill merge-to-maingit clone --depth 1 https://github.com/TheSmuks/ai-project-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/thesmuks/ai-project-template/merge-to-main)<a href="https://agentmods.dev/skills/thesmuks/ai-project-template/merge-to-main"><img src="https://agentmods.dev/badge/skills/thesmuks/ai-project-template/merge-to-main/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/thesmuks/ai-project-template/merge-to-main"><img src="https://agentmods.dev/badge/skills/thesmuks/ai-project-template/merge-to-main.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00022 | $0.01162 |
| Opus 5 | $0.00011 | $0.00581 |
| Sonnet 5 | $0.00004 | $0.00232 |
| Haiku 4.5 | $0.00002 | $0.00116 |
Grade A, and why
merge-to-main 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 12d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merge to Main
Automated PR lifecycle: prepare → create PR → monitor CI → fix failures → merge when green → update checkbox fields in the PR body.
When to Use
Invoke this skill after completing work on a feature branch, when you are ready to create or update a pull request and merge it into main.
Phase 1: Prepare
- Read
AGENTS.mdand.github/PULL_REQUEST_TEMPLATE.mdfor conventions. - Verify the current branch follows
<type>/<short-description>naming (e.g.feature/add-embeddings,fix/token-overflow). - Verify
CHANGELOG.mdhas been updated under[Unreleased](required bychangelog-check.yml). - If the working tree is dirty, stage and commit remaining changes.
- Push the branch to origin.
Phase 2: Create PR
- Read
.github/PULL_REQUEST_TEMPLATE.mdif it exists. - Check whether a PR already exists for this branch:
If one exists, skip creation and proceed to Phase 3.gh pr list --head <branch-name> --state open - Create the PR via
gh pr create:gh pr create --base main --title "<title>" --body "<body>"- Title: Extract from the first line of the most recent commit message (conventional commit format:
<type>[optional scope]: <description>). - Body: Fill in the PR template based on the changes. Leave "Automated checks" boxes unchecked — Phase 4 will update them.
- Draft: Create as ready-for-review by default. Use
--draftto create a draft PR instead.
- Title: Extract from the first line of the most recent commit message (conventional commit format:
Phase 3: Monitor CI
- Poll check status:
gh pr checks <pr-number> - Wait for all checks to reach a terminal state (
passorfail).- Poll interval: ~30 seconds
- Max wait: 10 minutes
- For each failing check:
a. Read the failure log:
bash gh run view <run-id> --log-failedb. Diagnose the issue. c. Fix the issue using appropriate tools (read, edit, search, ast_edit). d. Amend the last commit (if unpushed) or create a new fix commit. e. Push the fix. f. Re-enter the monitoring loop. - Max retries: 3 (to prevent infinite loops on unfixable issues).
- After 3 retries with failures, report what failed and stop — let the user decide.
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.
- 12d ago First seen · 113 lines · 22 tokens per session scan A 40bf1e401c55
merge-to-main is a skill published in the GitHub repository TheSmuks/ai-project-template (7 stars, last pushed 4mo ago), licensed MIT. It adds 22 tokens to every session and 1,162 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.
Other skills, from other repositories
github-cli
Automate GitHub workflows using the gh CLI for pull requests, issues, releases, actions, and repository management. Use when interacting with GitHub beyond basic git operations.
git-workflow-management
Git workflow automation skill for commit message generation, branch management, pre-commit checks, and change history analysis.
code-review-github
GitHub PR workflow orchestration for code review — list PRs, post comments, apply labels, and guarded auto-merge.
release-habit-hooks
Cut a new release of the habit-hooks packages. Use when asked to release, publish, or bump the version. Reviews what lands, enforces the in-sync versioning rule, validates the changelog, and drives the tag-triggered PyPI publish.
argot-setup
Set argot up for a repository end to end — audit its history, decide what should shape its voice, fit, verify the fit actually catches things, tune the rules its own history says are noisy, and wire the places it runs (pre-write hook, pre-commit, MCP, CI). One sitting, one decision at a time, each proposed with the…
codeflow-maintainer
OpenClaw-only maintainer PR workflow modes and skills. For OpenCoven/coven PR creation, redirect to skills/pr-agent, the Coven PR Readiness Agent.