What is approve-merge?

A workflow that records approval for one specifically named pull request or merge request and then merges it. A pull request is a proposed set of code changes for review.

Use it only after explicit approval of a particular pull request or merge request, to record that approval and perform the merge.

It prevents a general instruction such as “go” from being treated as approval to merge unrelated code.

approve-merge — Skill for Claude Code by me2resh/apexyard

Install

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.

Any agent

npx skills add me2resh/apexyard --skill approve-merge

Clone the repo

git clone --depth 1 https://github.com/me2resh/apexyard

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/me2resh/apexyard/approve-merge/github.svg)](https://agentmods.dev/skills/me2resh/apexyard/approve-merge)

Your own site

<a href="https://agentmods.dev/skills/me2resh/apexyard/approve-merge"><img src="https://agentmods.dev/badge/skills/me2resh/apexyard/approve-merge/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/me2resh/apexyard/approve-merge"><img src="https://agentmods.dev/badge/skills/me2resh/apexyard/approve-merge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,811 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00033	$0.03811
Opus 5.5	$0.00013	$0.01524
Sonnet 5.5	$0.00007	$0.00762
Haiku 4.5	$0.00003	$0.00381

Measured 15d ago against content hash 0433d42152e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

approve-merge 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 15d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (remove-worktree.sh, scripts/approve-merge.sh, tests/test_merge_invocation_not_substituted.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/approve-merge/SKILL.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing: read docs/skills/shared/writing-rule.md before you write a durable artifact.

/approve-merge — Record CEO Approval and Merge

Write per-PR approval, then merge through the tracker adapter. Rationale: read docs/skills/approve-merge-rationale.md for gate history and AgDR references.

The one rule you must not break

Invoke only on explicit user approval for this PR. A plan-level "go" is not merge approval. Stop and ask when the PR or intent is unclear. Only the human can invoke this skill (#1042).

The operator can also approve from one AskUserQuestion menu. Ask exactly Approve and merge <owner>/<repo>#<N> at <40-hex-sha>? with options Approve and merge and Not yet only. A hook writes the record; never write it yourself. See AgDR-0234.

Process

0. Resolve the configured approver display title (SOFT, prose-only)

Before addressing the user in any confirmation question or report, read the configured display title for the human per-PR merge approver:

source "$(git rev-parse --show-toplevel)/.claude/hooks/_lib-read-config.sh"
APPROVER_TITLE=$(config_get_or '.review_markers.human_approver_title' 'CEO')

Use $APPROVER_TITLE in prose only. Keep the -ceo filename and marker fields unchanged. If config or jq is unavailable, use CEO. This display setting must not block the skill.

1. Parse the PR number, the repo, and flags

Extract the PR number from $ARGUMENTS. If no number is given, try to infer from:

The current branch's open PR via gh pr view --json number --jq '.number'
The user's most recent message, if it named a PR explicitly

If the PR number is ambiguous (multiple PRs on the branch, unclear which was approved), STOP and ask the user which PR.

Resolve REPO from owner/repo#N or an explicit owner/repo argument. Otherwise, parse the current checkout's git remote get-url origin. Do not use ambient gh resolution or headRepository (#887). Scope each host query to REPO, then PR_HOST_REPO after step 4. Recognise --no-merge. It writes approval without merging.

Read the full file on GitHub · 292 lines

Files

What ships with it

3 files 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.

Changes

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.

15d ago Changed 0433d42152e7
22d ago Changed · -282 lines c730bb857535
29d ago Changed · +62 lines a4a8dbb89b0a
1mo ago Changed · +92 lines 6edf28d8e388
1mo ago Changed · +3 lines d7029c00273c
1mo ago Changed · +57 lines 75bb30ed29a7
2mo ago First seen · 360 lines · 33 tokens per session scan A 4265b88491fe

Subscribe to this mod's changes

approve-merge is a skill published in the GitHub repository me2resh/apexyard (542 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 3,811 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 2026-08-30.

Claude Code Git and workflow agentic-coding ai-agents ai-governance claude-code-hooks claude-code-skills

approve-merge next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
approve-mergeme2resh/apexyard	Skill	542	yesterday	MIT	A	33	Claude Code
deploy-landedavelikiy/great_cto	Skill	112	2d ago	MIT	A	103	Claude Code
signing-preflightavelikiy/great_cto	Skill	112	2d ago	MIT	A	105	Claude Code
releaseparcadei/Continuous-Claude-v3	Skill	3.9k	9mo ago	MIT	A	20	Claude Code
debugparcadei/Continuous-Claude-v3	Skill	3.9k	9mo ago	MIT	A	14	Claude Code
describe-prparcadei/Continuous-Claude-v3	Skill	3.9k	9mo ago	MIT	A	10	Claude Code
commitparcadei/Continuous-Claude-v3	Skill	3.9k	9mo ago	MIT	A	12	Claude Code

approve-merge