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 yongjip/mergetrain --skill candidategit clone --depth 1 https://github.com/yongjip/mergetrainWrote 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/yongjip/mergetrain/candidate)<a href="https://agentmods.dev/skills/yongjip/mergetrain/candidate"><img src="https://agentmods.dev/badge/skills/yongjip/mergetrain/candidate/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/yongjip/mergetrain/candidate"><img src="https://agentmods.dev/badge/skills/yongjip/mergetrain/candidate.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 | $0.00060 | $0.00587 |
| Opus 5.5 | $0.00024 | $0.00235 |
| Sonnet 5.5 | $0.00012 | $0.00117 |
| Haiku 4.5 | $0.00006 | $0.00059 |
Grade A, and why
mergetrain 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 1mo 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.
This is a copy
88% identical to mergetrain — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Integrate parallel coding-agent branches
Purpose: Serialize committed local task branches through one merge/test/push/verify runner.
Rules
- Work on a task-specific branch and worktree.
- Commit a clean HEAD before handing work off.
- Read mergetrain status --json and follow its next action before changing queue state.
- Enqueue every named finished branch in the requested order using only its task and branch; mergetrain resolves the worktree and captures the exact commits. Stop after the last successful enqueue unless the user explicitly authorized validation or the complete validation-and-deployment workflow.
- Never push configured integration refs directly. One authorized runner owns validation and deployment; recovery and destructive actions require their stated approval.
Safety boundary
- A task agent enqueues every named finished branch, then stops. "Queue for validation" authorizes enqueue only; only an explicit request to run validation or the complete end-to-end workflow authorizes
validate. - Only a separately authorized runner uses
deployor a daemon. - Deployment requires either confirmation of the human-readable exact plan or prior bounded unattended approval. Agents never select train IDs or supply plan hashes; structured evidence may include identifiers for inspection.
- Unattended approval is bound to the exact destination and execution policy. Any change blocks before push.
- Recovery and destructive cleanup require their stated approval. Follow
status.next_action; never rewrite permanent deploy audit refs.
Stable machine contract
- Every JSON payload carries
contract_version; ignore unknown keys and fail closed on unknown safety actions. deploymeans the atomic Git ref update plus configured verification. A downstream provider release is separate.
Use the plugin's MCP tools when they are available. Start with
mergetrain_status; its next action is guidance, not deployment authority.
Routine task agents call mergetrain_enqueue for every named committed, clean
branch in order and stop after the last successful handoff.
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.
- 1mo ago First seen · 46 lines · 60 tokens per session scan A 0e6d64df7287
mergetrain is a skill published in the GitHub repository yongjip/mergetrain (7 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 587 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to mergetrain, differing in 8 lines, and is treated as a copy.
Other skills, from other repositories
repo-hygiene
A repository hygiene audit and pre-commit gate for checking project files before a Git commit. Git is the system used to track code changes; the checks cover broken Markdown links, shell syntax, diagrams, possible secrets, and line-size limits.
batch-member-cites-a-path-only-a-non-member-adds
You wrote something correct that the default reader cannot reach: a batch member citing a path only a NON-member adds, or a rule, ruling or ledger sitting on an unlanded branch.
subagent-driven-branch-ref-froze-stranded-commits
Diagnose and recover from "PR merged, but half my work is missing from main" cases in superpowers:subagent-driven-development (or similar one-fresh-subagent-per-task) sessions, where committed work survives in the worktree's HEAD chain but never makes it into the pushed branch ref. Use when ANY of these appears: (1)…
git-add-u-after-async-post-commit-hook
Prevent (and recover from) git add -u + git commit --amend + git push --force-with-lease catastrophically rolling thousands of unrelated tracked-file deletions into an amended commit when the project has an async post-commit hook that mutates tracked files (e.g. regenerates docs/site/.html, docs/site/index.html…
async-post-commit-hook-commit-orphaned-by-squash-merge
In a repo with an ASYNC/background post-commit hook (one that fires after a commit and creates its OWN follow-up commit — [auto-docs] …, a docs/site regen, a changelog/checkbox tick), the hook's commit can land LOCAL-ONLY after your git push already captured just your work commit, so it is never in the PR and gets…
working-tree-edits-stranded-on-squash-merge
Diagnose and prevent "I made the fix but it's not on main" cases where the fix was applied in the working tree via Edit / Write but never git added before the squash-merge. Use when: (1) you squash-merged a PR and the user reports the issue is back, (2) git status after the merge shows uncommitted changes for files…