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 SethGammon/Citadel --skill merge-reviewgit clone --depth 1 https://github.com/SethGammon/CitadelWrote 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/sethgammon/citadel/merge-review)<a href="https://agentmods.dev/skills/sethgammon/citadel/merge-review"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/merge-review/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/sethgammon/citadel/merge-review"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/merge-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00040 | $0.01596 |
| Opus 5 | $0.00020 | $0.00798 |
| Sonnet 5 | $0.00008 | $0.00319 |
| Haiku 4.5 | $0.00004 | $0.00160 |
Grade A, and why
merge-review 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 10d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/merge-review — Fleet Merge Arbitration
Orientation
Use when: reviewing pending fleet worktree merges before accepting them into the main branch. Don't use when: reviewing general code quality (use /review); checking CI status before merging (use /pr-watch).
When to Route Here
- "check merges"
- "any conflicts"
- "what do the fleet agents want to merge"
- "review the pending branches"
- "is it safe to merge fleet output"
- "arbitrate the worktrees"
- worktree-remove.js has queued items and the user wants to process them
Invocation Forms
/merge-review # Process the full queue
/merge-review {branch} # Review a specific branch only
Protocol
Step 1: Read the Queue
Read .planning/telemetry/merge-check-queue.jsonl. Each line is a JSON object:
{"branch": "fleet/task-abc", "worktree": "/path/to/worktree", "queuedAt": "ISO"}
If the file doesn't exist or is empty:
"No pending merge reviews. Fleet agents haven't completed any worktrees recently." Stop here.
If invoked with a specific branch (/merge-review {branch}): filter to that branch only.
Step 2: For Each Branch — Gather Diff Data
Run git diff main..{branch} --name-only, --stat, and git branch --list {branch}.
If the branch no longer exists: mark status: "merged", note "likely already merged. Skipped.", continue.
Step 3: Detect Overlapping Files
Compare changed file sets pairwise. For each pair sharing files, read git diff main..{branch} -- {file} for both and classify:
- Additive: both add to the file (low risk, likely auto-mergeable)
- Overlapping edits: both modify the same function/section (medium risk)
- Contradictory: one adds, the other removes the same code (high risk)
Step 4: Assess Risk Per Branch
For each branch:
- low — no overlapping files with other branches
- medium — overlaps exist but changes appear additive or in different sections
- high — overlaps in the same function, class, or closely coupled section
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.
- 10d ago First seen · 192 lines · 40 tokens per session scan A 9ef6c0900179
merge-review is a skill published in the GitHub repository SethGammon/Citadel (920 stars, last pushed 6d ago), licensed MIT. It adds 40 tokens to every session and 1,596 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
github-backlog-triage
Use when the user invokes backlog triage for a GitHub repo's open issues and PRs. Not for proactive triage, non-GitHub trackers, or single bug issues: use github-bug-report-triage.
git-history-analysis
Use when the user asks about recent engineering work, what the team is working on, planning or roadmap material, or an explicitly requested Slack summary. Not for remote or irreversible changes.
atomic-issues-prs
Use when the user says "atomic PRs" or requests one issue or PR per logical change. Don't use for single-change pushes or uncommitted change-sets.
post-merge-cleanup
Use when a landed merge, release, or completed change needs its cleanup surface reconciled. Scans for stale TODOs, deprecations, unused flags, and doc gaps. Not for unrelated refactoring.
unleash
Run as a named worker draining the task queue in my private coordination repo, where each task is a GitHub Issue — claim one task at a time, check blocked-by dependencies, plan with explicit assumptions, execute, validate against acceptance criteria, and record results as comments; then stay in ambush behind a…
vibe-status
Use when you want a snapshot of all active vibe-kanban workspaces, their PRs, and any inconsistencies - shows dashboard-style table with workspace state, branch, PR status, CI, and review state, flags anything stuck or inconsistent.