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 deploygit 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/deploy)<a href="https://agentmods.dev/skills/yongjip/mergetrain/deploy"><img src="https://agentmods.dev/badge/skills/yongjip/mergetrain/deploy/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/deploy"><img src="https://agentmods.dev/badge/skills/yongjip/mergetrain/deploy.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 | $0.00030 | $0.00225 |
| Opus 5.5 | $0.00012 | $0.00090 |
| Sonnet 5.5 | $0.00006 | $0.00045 |
| Haiku 4.5 | $0.00003 | $0.00022 |
Grade A, and why
deploy 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.
What it actually says
Deploy one exact plan
- Call
mergetrain_statusand read its health, state, and next action. - Invoke
mergetrain_deploywithout selection or approval arguments. It may validate queued work, then presents the exact tasks, destination refs, and gate policy through the client's human confirmation dialog. Neither the agent nor the operator selects a train ID or supplies a plan hash; structured evidence may retain identifiers for inspection. - Do not substitute a shell deploy command or a model-supplied confirmation.
If the tool returns
confirmation_required, show its terminal command and stop. If it returnsdeploy_not_confirmed, report that nothing was pushed. - Report
result, deployed job IDs,deploy_sha,push_status, andverify_status.
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 Changed · +1 lines 3aabf28d8f41
- 1mo ago Changed · +14 tokens per session 9afb361f543a
- 1mo ago First seen · 22 lines · 16 tokens per session scan A e8471c2189e8
deploy is a skill published in the GitHub repository yongjip/mergetrain (7 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 225 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
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…
gh-pr-merge-unstable-state-needs-auto-and-watch-branch-deletes
Diagnose and recover from two adjacent gh pr merge failure modes that masquerade as merge conflicts. Use when: (1) gh pr merge --squash (or --merge) errors with "To have the pull request merged after all the requirements have been met, add the --auto flag" AND "Run the following to resolve the merge conflicts locally"…
merge-queue-thrash-stop-inflow-and-open-prs-as-drafts
When main moves faster than the slowest CI leg, every open branch goes stale before it can merge and the whole queue jams with nothing red. Use when: (1) several PRs sit at mergeStateStatus BEHIND with auto-merge armed and none of them lands; (2) branches are being updated, re-running CI and going stale again before…
scheduled-fallback-check-cites-stale-task-id
Don't act on a background-task ID embedded in an incoming check-in message (a self-scheduled fallback wakeup, a peer's "did it finish?" ping, a cron reminder) without first verifying it's still the CURRENT run. Use when: (1) you dispatched a long-running background task (a local CI-equivalent gate run, a build, a…
subagent-reports-complete-but-pr-unmerged
Catch the systematic gap between sub-agent "completed" status and the actual end state of a PR-merge orchestration task. Use when: (1) you've dispatched multiple parallel sub-agents (general-purpose or specialist) to open + review + merge PRs, (2) the parent receives with status: completed but the sub-agent's last…
crow-release-review
Study everything on main since each repo's last release, publish a release review page (a private claude.ai Artifact) with what changes for users, a plain-language before and after, risks, blockers, a phased runbook and post-release test steps, then read the operator's notes and decisions back, help run each tag only…