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 EZotoff/ez-omo-config --skill merge-agent.tmpgit clone --depth 1 https://github.com/EZotoff/ez-omo-configWrote 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/ezotoff/ez-omo-config/merge-agent.tmp)<a href="https://agentmods.dev/skills/ezotoff/ez-omo-config/merge-agent.tmp"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/merge-agent.tmp/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/ezotoff/ez-omo-config/merge-agent.tmp"><img src="https://agentmods.dev/badge/skills/ezotoff/ez-omo-config/merge-agent.tmp.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 | $0.00000 | $0.01981 |
| Opus 5.5 | $0.00000 | $0.00792 |
| Sonnet 5.5 | $0.00000 | $0.00396 |
| Haiku 4.5 | $0.00000 | $0.00198 |
Grade A, and why
merge-agent.tmp 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.
This is a copy
100% identical to merge-agent — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/merge-worktree
Safely merge a worktree branch into main with strict local state tracking, lock discipline, and deterministic rollback.
Header
- Name:
merge-agent - Description: Safely merge worktree branches into main with state tracking and conflict resolution
- Triggers:
/merge-worktree,merge branch,integrate worktree
Usage
/merge-worktree <branch>
/merge-worktree --branch=<branch>
Optional runtime context:
project-id: Used for state path resolution under~/.local/share/opencode/worktree-state/<project-id>/session-id: Used for merge lock ownership (lockedBy)
Overview
This skill performs a guarded local-only merge flow:
- Pre-Merge Validation — ensure we are in a feature worktree and clean
- Merge Lock Acquisition — serialize merges via
merge.lock - Rebase Before Merge — rebase branch onto
origin/main - Merge Execution — merge from the main worktree, never from feature worktree context
- Post-Merge Cleanup — finalize state, release resources, remove worktree
- Rollback — deterministic failure handling for each failure mode
Pre-Merge Validation
1) Verify we are in a worktree (NOT primary main checkout)
Run:
git rev-parse --git-common-dir
Rules:
- If result equals
.git(or resolves to primary checkout root), STOP. - Merge execution must originate from a feature worktree session, but actual merge command runs in the main worktree path using
git -C.
2) Verify working tree is clean
Run:
git status --porcelain
Rules:
- Any output means uncommitted changes exist.
- STOP until all changes are committed.
3) Load branch state
Read state file:
~/.local/share/opencode/worktree-state/<project-id>/worktrees/<branch>.json
Validate:
- file exists
branchmatches target branchstatusis eligible (readyormergingrecovery state)worktreePathexists
If validation fails: mark state failed if possible 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.
- 11d ago First seen · 302 lines · 0 tokens per session scan A 6bbf5d3d6e23
merge-agent.tmp is a skill published in the GitHub repository EZotoff/ez-omo-config (6 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,981 tokens. A static security scan graded it A with 0 findings. It is 100% identical to merge-agent, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
project-session-manager
Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions.
release
Generic release assistant — analyzes repo release rules, caches them in .omc/RELEASERULE.md, then guides the release.
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
worktrees
Manage Git worktrees as OMO safe isolated coding lanes for complex, risky, or parallel work.
finishing-a-development-branch
Use when development work is complete and you need to prepare for merge. Guides through cleanup, testing, documentation, and creating a well-structured pull request.
armada-voyage-finish
Voyage-finalization ritual. Load at voyage end, dispatch a galleon subagent to rebase, fix TODO PR refs, regen scaffold, push, open/update PR. Triggers on: finish voyage, finalize, rebase, PR.