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 sequant-io/sequant --skill mergergit clone --depth 1 https://github.com/sequant-io/sequantWrote 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/sequant-io/sequant/merger)<a href="https://agentmods.dev/skills/sequant-io/sequant/merger"><img src="https://agentmods.dev/badge/skills/sequant-io/sequant/merger/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/sequant-io/sequant/merger"><img src="https://agentmods.dev/badge/skills/sequant-io/sequant/merger.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 | $0.00020 | $0.07823 |
| Opus 5.5 | $0.00008 | $0.03129 |
| Sonnet 5.5 | $0.00004 | $0.01565 |
| Haiku 4.5 | $0.00002 | $0.00782 |
Grade A, and why
merger 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 13d 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 — 817 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Local overrides (read this first). Before following any instruction below, check whether
.claude/.local/skills/merger/overrides.mdexists. If it does, read it and treat its contents as authoritative: its instructions take precedence over anything in this skill they conflict with. This is the supported way to tailor/mergerwithout forking it —overrides.mdlives under.claude/.local/, whichsequant updateandsyncnever overwrite.
Merger Skill
You are the "Merger Agent" for handling post-QA integration of completed worktrees.
Purpose
When invoked as /merger <issue-numbers>, you:
- Capture baseline metrics on main (build errors, test counts)
- Validate QA status for all specified issues
- Detect file conflicts between worktrees
- Generate integration branches for incompatible changes
- Respect dependency ordering
- Clean up worktrees after successful merge
- Run post-merge smoketest with regression comparison against baseline
- Provide detailed merge reports
Recommended Pre-Merge Check
Before running /merger, use sequant merge --check to catch cross-issue gaps at zero AI cost:
sequant run 10 11 12 # implement
sequant merge --check # verify (deterministic checks)
/merger 10 11 12 # merge (this command)
sequant merge detects merge conflicts, template mirroring gaps, file overlaps, and residual patterns before /merger attempts the actual merge. See docs/reference/merge-command.md for details.
Usage
# Merge single issue
/merger 10
# Merge multiple issues (detects conflicts, creates integration if needed)
/merger 10 12
# Merge with dependency ordering
/merger 10 12 --order=dependency
# Dry run - show what would happen
/merger 10 12 --dry-run
# Force parallel validation of multiple issues (faster, higher token usage)
/merger 10 12 --parallel
# Force sequential validation (slower, lower token usage)
/merger 10 12 --sequential
# Skip post-merge smoketest
/merger 10 12 --skip-smoketest
# Force merge even if regression is detected (bypasses regression gate)
/merger 10 12 --force
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.
- 13d ago Changed · +13 lines 4646115ff6c3
- 18d ago Changed · +62 lines b2ada1daac13
- 1mo ago First seen · 742 lines · 20 tokens per session scan A efd11687ce75
merger is a skill published in the GitHub repository sequant-io/sequant (1 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 7,823 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
shipyard-verification
Requires fresh verification evidence before any claim that work is complete, fixed, or passing. Use before committing, creating PRs, or moving to the next task. Also use when a status report contains words like "should", "probably", or "seems to", or expresses satisfaction ("Great!", "Done!") before verification…
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
refactor
Refactor existing code by extracting helpers, splitting files, removing duplication, or untangling dependencies. Supports resumable and batch runs. Use for structural changes that preserve behavior; use zuvo:build for new features.
coverage-check
Run the repo's unit tests with coverage and verify that every file touched in the current change keeps line, branch, and function coverage at or above 95%. Language- and framework-agnostic. Use before committing, before PR creation, or when the user asks about coverage.
commit
A Git workflow skill that completes a TDD cycle by committing changes after required review, tests, logs, and retrospective checks pass. Git is a version-control system that records code changes and commits.
wrap-up-branch
Finish a feature branch: add missing tests, review and fix the code, align docs, then merge only after explicit confirmation.