Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add pleaseai/claude-code-plugins/plugin install graphiteWrote 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/commands/pleaseai/claude-code-plugins/merge-queue)<a href="https://agentmods.dev/commands/pleaseai/claude-code-plugins/merge-queue"><img src="https://agentmods.dev/badge/commands/pleaseai/claude-code-plugins/merge-queue/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/commands/pleaseai/claude-code-plugins/merge-queue"><img src="https://agentmods.dev/badge/commands/pleaseai/claude-code-plugins/merge-queue.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 | $0.00015 | $0.01195 |
| Opus 5 | $0.00008 | $0.00598 |
| Sonnet 5 | $0.00003 | $0.00239 |
| Haiku 4.5 | $0.00002 | $0.00120 |
Grade A, and why
merge-queue 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add or remove the configured Graphite merge-queue label on a pull request. User input: $ARGUMENTS.
Graphite's merge queue is driven entirely by a label — applying it enqueues; removing it dequeues. For stacked PRs, the label cascades to dependent PRs automatically (label the topmost PR you want merged; do not iterate).
Resolve config (enabled gate, mode, label)
All parsing is centralized in ${CLAUDE_PLUGIN_ROOT}/scripts/read-merge-queue-config.sh, which emits three KEY=VALUE lines. eval the output, then apply env-var overrides:
eval "$("${CLAUDE_PLUGIN_ROOT}/scripts/read-merge-queue-config.sh")"
# Env-var overrides (caller can force a value without editing .please/config.yml)
MERGE_MODE="${GRAPHITE_MERGE_QUEUE_MODE:-$MERGE_MODE}"
MERGE_LABEL="${MERGE_QUEUE_LABEL:-${MERGE_LABEL:-merge-queue}}"
# 1. Bail if graphite is disabled.
if [ "$GRAPHITE_DISABLED" = "1" ]; then
echo "graphite.enabled: false in .please/config.yml — repo opted out of Graphite. Skipping."
exit 0
fi
# 2. Dispatch on mode. Only `graphite` continues with the label flow.
case "$MERGE_MODE" in
graphite) ;; # continue below
"") echo "merge-queue.mode not configured in .please/config.yml. Ask the user which mode the repo uses, then persist it."; exit 0 ;;
*) echo "Repo uses '$MERGE_MODE' merge queue, not Graphite's. Skipping label flow."; exit 0 ;;
esac
Modes that this command does NOT handle
| Mode | What to do instead |
|---|---|
github-native |
gh pr merge --auto --squash (or chosen strategy) — GitHub queues automatically |
external |
Defer to the external tool (Mergify/Kodiak/etc.) — apply its enqueue label, not Graphite's |
none |
gt submit --merge for stacks, or gh pr merge for a single PR |
| unset | Ask the user which mode the repo uses, then offer to persist it to .please/config.yml |
Resolution precedence
- Mode:
GRAPHITE_MERGE_QUEUE_MODEenv var →graphite.merge-queue.modein.please/config.yml→ empty (caller asks). - Label:
MERGE_QUEUE_LABELenv var →graphite.merge-queue.labelin.please/config.yml→merge-queue(default). - Disabled gate: only
graphite.enabled: falseat the immediate child ofgraphite:triggers bail-out; the script's depth-tracking ignores nestedenabledkeys.
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 · 82 lines · 15 tokens per session scan A be789849d535
merge-queue is a command published in the GitHub repository pleaseai/claude-code-plugins (13 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 1,195 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 2026-09-07.
Other commands, from other repositories
land
Cadence-tick autonomous PR babysitter (CI-fix, resolve, converge, merge, close, release).
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
ship
Ship is the operational release-prep flow for a connected project repo.
release-plan
A release-planning command for a software change. It documents the release scope, rollback plan, gradual or full rollout, and monitoring before waiting for human approval.
release
Standalone SDK release command for the BUILD repo. Not a workspace phase — runs independently after any number of implement/redteam cycles. Handles PyPI publishing, documentation deployment, and CI management for the kailash Python SDK and its framework packages.
create-pr
Push the current branch and open a pull request into main with a structured description derived from the branch's commits and issue references.