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 nirecom/agents --skill merge-to-maingit clone --depth 1 https://github.com/nirecom/agentsWrote 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/nirecom/agents/merge-to-main)<a href="https://agentmods.dev/skills/nirecom/agents/merge-to-main"><img src="https://agentmods.dev/badge/skills/nirecom/agents/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/nirecom/agents/merge-to-main"><img src="https://agentmods.dev/badge/skills/nirecom/agents/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 | $0.00037 | $0.01015 |
| Opus 5.5 | $0.00015 | $0.00406 |
| Sonnet 5.5 | $0.00007 | $0.00203 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
merge-to-main scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Perform the delivery operation the user approved in /get-release-approval, then complete the merge_to_main step.
Every step is idempotent: a re-run after a partial delivery resumes without repeating a landed operation.
Procedure
When a hook blocks a sanctioned command, a fallback path is taken, or any unexpected outcome occurs, report via /supervisor-report (trigger conditions: rules/supervisor-reporting.md).
MM-1. Confirm the step: run node "$AGENTS_MAIN_ROOT/bin/workflow/next-step" --session "<session-id>".
REASON= other than merge_to_main → stop and follow its ACTION; never merge or push before the approval is recorded.
MM-2. Read the delivery path: run node "$AGENTS_MAIN_ROOT/bin/session-close-detect-route.js" --session "<session-id>" and read ROUTE= (the recorded delivery_path).
pull_request → run node "$AGENTS_MAIN_ROOT/bin/workflow/release-channel" --session "<session-id>" and read CHANNEL=, then MM-3.
direct → MM-4.
Pull request delivery
MM-3. Merge the PR (pull_request): run node "$AGENTS_MAIN_ROOT/bin/workflow/pr-state" and read PR_STATE= / PR_NUMBER=.
MERGED → already delivered; go to MM-5.
OPEN with release-channel CHANNEL=web-merge → the human merges on the web; never merge here — stop and run /get-release-approval.
OPEN and PR_NUMBER differs from the PR number in the /get-release-approval GA-3 approval reason → stop and re-run /get-release-approval instead of merging.
OPEN → issue the merge as one direct Bash call, never wrapped in a helper:
github: gh pr merge <PR_NUMBER> --squash --delete-branch
gitlab: glab mr merge <PR_NUMBER> --squash --remove-source-branch
Merge failure → surface the error and stop; on success go to MM-5.
NONE → run bash "$AGENTS_MAIN_ROOT/bin/probe-remote-bootstrap.sh" "<WORKTREE_PATH>"; preBootstrap true with classification empty-repo (the /commit-push outcome was bootstrap_pending) → MM-3b; otherwise go to MM-5, which accepts an earlier bootstrap push and refuses when /commit-push never opened the PR.
CLOSED or UNKNOWN → surface the state and stop.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 57 lines · 37 tokens per session scan A 720e9317f189
merge-to-main is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 1,015 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 2026-10-14.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
release
Fully automate a release with version-bump and childhood.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.