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 baselinegit 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/baseline)<a href="https://agentmods.dev/skills/yongjip/mergetrain/baseline"><img src="https://agentmods.dev/badge/skills/yongjip/mergetrain/baseline/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/baseline"><img src="https://agentmods.dev/badge/skills/yongjip/mergetrain/baseline.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 | $0.00075 | $0.00614 |
| Opus 5.5 | $0.00030 | $0.00246 |
| Sonnet 5.5 | $0.00015 | $0.00123 |
| Haiku 4.5 | $0.00007 | $0.00061 |
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- mergetrain — 88% identical, 8 lines differ
How it starts
The opening of the file, as written. The whole thing — 52 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 · 52 lines · 75 tokens per session scan A 3c083b1fa32f
mergetrain is a skill published in the GitHub repository yongjip/mergetrain (7 stars, last pushed today), licensed MIT. It adds 75 tokens to every session and 614 once invoked, about $0.0003 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 2026-09-05.
Other skills, from other repositories
blueprint-refactor-tranche
Take ONE target from the plan and land it without changing behaviour: guard it on the untouched code, move it verbatim, prove the equivalence by running both, mutation-sweep the tests, pass every gate, open a PR and merge it on green CI — or decline it with the cost written down.
blueprint-repo-baseline
Find the repository's own gates — install, format check, lint, typecheck, build, test — record them, and prove they all pass before anything is touched.
blueprint-repo-ci
Find out whether GitHub Actions already runs the recorded gates on every pull request, and record what is missing. Change nothing: adding CI is the first change the person approves.
blueprint-repo-state
Confirm the folder is a clean clone of a GitHub repository on its up-to-date default branch, and keep the build's own notes out of git.
blueprint-docs-workspace
Make sure chaff runs in this document folder and that the build's records have a place, before anything is read or written.
crow-ci-queue
Serialize the label-gated ci:full suite across the PRs of live Crow sessions — per repo, exactly one session PR holds ci:full, runs the full suite and merges; then the next ready PR is updated from main and labeled. Strips the extras, orders the rest, and waits on a background watcher. Keeps running after a repo…