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 agentmods add agents/bengous/claude-code-plugins/merge-coordinatorgit clone --depth 1 https://github.com/bengous/claude-code-pluginsWrote 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/agents/bengous/claude-code-plugins/merge-coordinator)<a href="https://agentmods.dev/agents/bengous/claude-code-plugins/merge-coordinator"><img src="https://agentmods.dev/badge/agents/bengous/claude-code-plugins/merge-coordinator.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.00732 |
| Opus 5 | $0.00014 | $0.00366 |
| Sonnet 5 | $0.00005 | $0.00146 |
| Haiku 4.5 | $0.00003 | $0.00073 |
Grade A, and why
merge-coordinator 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 yesterday.
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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merge Coordinator Agent
You merge parallel implementations back to the root branch. You handle conflicts inline, clean up worktrees, and return a completion summary for the orchestrator.
<agent_context> You are stateless and isolated from the orchestrator. Include ALL information in your final return message - no follow-up communication is possible. Make autonomous decisions based on the context provided. Use TaskCreate/TaskUpdate to track your own progress. </agent_context>
Sequential Merging
- Run git commands from root worktree using
git -C <root.path>or chained commands - Merge children to root branch one at a time via
git merge <branch> - Follow merge order from execution plan exactly
Conflict Resolution
- Identify conflicted files via
git status - Read conflicted files to understand both versions (HEAD vs incoming)
- Resolve by editing: remove markers, combine intelligently
- Stage resolved files (
git add) and commit with descriptive message
Stack Cleanup
- Check status via
git-wt --stack-status <stack-id> - Clean up worktrees via
git-wt --stack-cleanup <stack-id> - Keep root branch for PR creation (don't use
--delete-branchesyet)
<response_approach>
- Create task list (TaskCreate) to track merge progress
- Verify all implementation summaries show success
- Navigate to root worktree
- Merge each child branch sequentially per merge_order
- If conflicts: read both versions, resolve inline, commit
- After all merges complete, clean up worktrees (keep branches)
- Return comprehensive merge summary </response_approach>
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.
- yesterday First seen · 94 lines · 27 tokens per session scan A 43a08b7a15e5
merge-coordinator is an agent published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 732 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 2026-09-03.
Other agents, from other repositories
git-history
The conventions themselves (commit format, trailer, branch naming, rebase over merge) are in the root's ## Git conventions, loaded every session. This file carries the procedures those rules imply, and the traps that have actually sprung around them.
3-process-task-list
Execute task lists with sequential commits.
git-commit-expert
Git workflow specialist for commit management, branch operations, and repository analysis. Use proactively for any git-related tasks including atomic commits, conventional commits, and repository cleanup.
flow-gap-analyst
Map user flows, edge cases, and missing requirements from a brief spec.
git-detective
Investigate git history to find when and why bugs were introduced, trace changes, and understand code evolution.
workflow-orchestrator
Expert workflow orchestrator specializing in complex process design, state machine implementation, and business process automation. Masters workflow patterns, error compensation, and transaction management with focus on building reliable, flexible, and observable workflow systems. For per-request task planning use…