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 sawy3r/baton --skill baton-mergegit clone --depth 1 https://github.com/sawy3r/batonWrote 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/sawy3r/baton/baton-merge)<a href="https://agentmods.dev/skills/sawy3r/baton/baton-merge"><img src="https://agentmods.dev/badge/skills/sawy3r/baton/baton-merge/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/sawy3r/baton/baton-merge"><img src="https://agentmods.dev/badge/skills/sawy3r/baton/baton-merge.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 | $0.00017 | $0.00569 |
| Opus 5 | $0.00009 | $0.00284 |
| Sonnet 5 | $0.00003 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
baton-merge 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use the invoking request as input. Resolve relative files from this directory. This standalone skill needs no shared Baton folder.
operation: baton-merge version: baton.operation/v2
Purpose
Combine passed work or merge the exact complete release covered by current
PASS.
Inputs
- The approved plan revision and one saved Git snapshot.
- For a track, the passed slices in approved order.
- For the release, the exact assembled candidate and fresh assembly
PASS.
Authority
Merge never invents a verdict or resolves a product conflict. Get candidates, order, and expected targets from approved facts. Stop before an unsafe change; the surrounding system may then rescan and recover. Merge acts on the exact passed candidate, including verified support work, not a predicted file list.
Actions
- For a track, prove every required slice has an applicable
PASS, hold the exact candidate still, and combine it in the approved order. - After all tracks pass, assemble the latest target with those exact products
and stop for fresh
baton-verifyassembly. A later target advance rebuilds and rechecks only this assembly; it does not reset unchanged slices. - For release Merge, recheck the assembly
PASS, candidate, authority, and expected target immediately before integration. - Perform the exact Git change and read the resulting target.
- On an exact retry, return the already observed canonical result without duplicating the effect.
Required output
Lead with what happened, what it means, and what happens next. Put scope, pass
bindings, component candidates, expected and observed targets, and resulting
commit under technical details for the machine-written receipt. Never report
partial success as MERGED.
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 First seen · 71 lines · 17 tokens per session scan A 1c9c4994604b
baton-merge is a skill published in the GitHub repository sawy3r/baton (9 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 569 once invoked, about $0.0001 per session on Opus 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
resolve-pr-comments
This skill should be used when user asks to "address PR comments", "resolve PR feedback", "handle review comments", "fix PR issues", "respond to PR review", or explicitly invokes "resolve-pr-comments".
review-pr
This skill should be used when user asks to "review a PR", "review pull request", "review this pr", "code review this PR", "check PR.
create-pr
Create pull requests following Sentry conventions. Use when opening PRs, writing PR descriptions, or preparing changes for review. Follows Sentry's code review guidelines.
gitlab-create-mr
Create GitLab merge requests from a local branch using a reviewable workflow for branch checks, GitLab host detection, diff analysis, title and description writing, and glab mr create. Use when opening a GitLab merge request, drafting or improving merge request copy, preparing a branch for review, or working across…
codex-review
Professional code review with auto CHANGELOG generation, integrated with Codex AI.
code-review
Request or perform a git-backed code review for a defined diff or SHA range using implementation context and requirements. Use when finishing a task, completing a major feature, preparing to merge, or when you need a fresh review before proceeding.