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 sweep-branchesgit 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/sweep-branches)<a href="https://agentmods.dev/skills/nirecom/agents/sweep-branches"><img src="https://agentmods.dev/badge/skills/nirecom/agents/sweep-branches/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/sweep-branches"><img src="https://agentmods.dev/badge/skills/nirecom/agents/sweep-branches.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 | $0.00027 | $0.00398 |
| Opus 5.5 | $0.00011 | $0.00159 |
| Sonnet 5.5 | $0.00005 | $0.00080 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
sweep-branches 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 11d 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
Reclaims merged-but-undeleted local and remote branches. Local branches are
age-gated (default 24 h); remote branches are only PR-merged checked. Protected
branches (main, master, develop, release/*) are never deleted.
Procedure
SB-1. Resolve $AGENTS_MAIN_ROOT from the environment; abort with a clear error
if unset.
SB-2. Invoke the sweeper script (no flag = deletes; --dry-run = preview):
bash "$AGENTS_MAIN_ROOT/bin/sweep-branches.sh" [--dry-run] [--min-age-hours N] [--ci-mode]
SB-3. Print the script's stdout verbatim. Do not summarize or filter.
Forward the user's flags verbatim. Add no flags of your own.
Rules
- Deletes by default;
--dry-runmust be explicit to preview only. --delete-no-pralone deletes no-PR local branches; add--dry-runto preview.- Remote branches use
gh api -X DELETE(REST API); local branches usegit branch -DwithSWEEP_BRANCHES_SKILL=1guard. - Remote branches are not age-gated (only PR-merged check); local branches are age-gated via
--min-age-hours. main,master,develop,release/*are never deleted.- Non-GitHub remotes are skipped (non-fatal).
- Per-branch failures are non-fatal: warning printed, sweep continues.
- After remote deletion, local tracking refs (
origin/<branch>) persist untilgit fetch --prune.
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.
- 11d ago Changed 12df43dd66e7
- 1mo ago First seen · 33 lines · 27 tokens per session scan A b9939a58ba0d
sweep-branches is a skill published in the GitHub repository nirecom/agents (3 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 398 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
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
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.