post-merge

post-merge is a skill for Claude Code from YoungjaeDev/my-claude-plugins. It costs 167 tokens per session (8,160 once invoked), scanned B, original, MIT.

A procedure for after a pull request merges, meaning proposed code has been accepted into the main project. It cleans up the local branch, updates project tracking, records knowledge, and commits the changes.

In plain words
What is it for?
Use it from the main repository to confirm a merged pull request, clean up branches, update tracking and wiki information, refresh the README, and commit the result.
Why use it?
It gathers the follow-up work in one process so merged changes are reflected in configuration, documentation, and the project wiki.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Part of the dev plugin — 12 skills shipped together

Good fit Use it from the main repository to confirm a merged pull request, clean up branches, update tracking and wiki information, refresh the README, and commit the result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/youngjaedev/my-claude-plugins/post-merge
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 YoungjaeDev/my-claude-plugins --skill post-merge
Clone the repo
git clone --depth 1 https://github.com/YoungjaeDev/my-claude-plugins

Made for: Claude Code.

Or install dev, the plugin that ships this one along with the rest of its 12 skills.

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.

agentmods badge for post-merge

README.md
[![agentmods](https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/post-merge/github.svg)](https://agentmods.dev/skills/youngjaedev/my-claude-plugins/post-merge)
Your own site
<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/post-merge"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/post-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.

agentmods 80×15 button for post-merge

Your own site · 80×15
<a href="https://agentmods.dev/skills/youngjaedev/my-claude-plugins/post-merge"><img src="https://agentmods.dev/badge/skills/youngjaedev/my-claude-plugins/post-merge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 167 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,160 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00167 $0.08160
Opus 5 $0.00084 $0.04080
Sonnet 5 $0.00033 $0.01632
Haiku 4.5 $0.00017 $0.00816

Measured 4d ago against content hash 9012155a4220, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

post-merge scanned grade B with 1 finding 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

**6.1 Cross-file dedup gate (run before writing any learning).** For each fact, first grep the SSOT set (`CLAUDE.md`, `AGENTS.md`, the relevant `.claude/rules/*.md`) for an existing home. If one exists, **update that lin
plugins/dev/skills/post-merge/SKILL.md · 347 lines

How it starts

The opening of the file, as written. The whole thing — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Post-Merge

Local cleanup + knowledge integration after a PR is merged. One run takes a merged PR from branch cleanup → tracking sync → config/memory integration → mandatory wiki-lore ingest → README → commit. Follow project guidelines in @CLAUDE.md and @AGENTS.md throughout.

For worktree removal, use /exit with its cleanup option.

Guidelines

  • Worktree guard (P0). post-merge must run from the main repo, not a worktree: Step 3 checks out the base branch, which collides with the original repo's checkout. The Step 1 guard aborts when run inside a worktree.
  • gh pr view is the authoritative merge signal. Step 1's gh pr view ... state=MERGED is the single source of truth for "did this land". Later steps MUST NOT re-verify merge state by comparing git SHAs.
  • Never use SHA-level merge comparison. git log <base>..<branch>, git cherry, git rev-list --left-right all false-positive after squash merge (base gets one new SHA) and rebase merge (branch SHAs rewritten). If unsure content landed, diff content not SHAs (Step 4).
  • No stamps, current-state only. Normative docs hold current rules; provenance lives in git/PR/blame. No (#N) / PR #N / 이슈 #N citations, no ## Post-Merge headers. Full rules + the <!-- history-allowed [max=N] --> opt-out + language consistency + SSOT cross-file dedup + content-first: see references/core-principle.md.
  • Knowledge routing (no double-recording). Mechanical / tool-operation rules → CLAUDE.md / AGENTS.md / .claude/rules/ / Serena memory (Steps 6-7). Cross-agent lore (provider quirks, design rationale, debugging stories) → .llmwiki/ via the wiki step (Step 8). Each fact is recorded in exactly one home; the wiki step (run after config integration) dedups against what Steps 6-7 already absorbed. Cross-agent rules that graduate do so to .llmwiki/insight/ via the wiki step, never to .claude/rules/ (Codex can't read it).
  • Leftover-review surface (Step 1.5) is informational. The run reads cr-fix's state file (.claude/state/cr-fix-<PR>.json, else the latest .claude/state/archive/ copy) to surface autonomously-deferred or cap/timeout-stopped findings after the merge, but never blocks cleanup. It always prints one leftover-reviews: … checkpoint line (mirroring the Step 8 wiki checkpoint) so a skip can't pass unnoticed. gh / jq / Read only → identical under Claude and Codex.
  • Codex partial-execution. Under Codex 0.135 the Serena (Step 7), docs:write-rules / claude-md-management:claude-md-improver (Step 6.5), and humanize-korean / docs:readme (Step 9) sub-steps are Claude-only; gracefully skip them and note the skip rather than failing.

Read the full file on GitHub · 347 lines

Files

What ships with it

5 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.

  1. 4d ago Changed · +6 lines · -93 tokens per session 9012155a4220
  2. 9d ago First seen · 341 lines · 260 tokens per session scan B 6c6e88f313a0

Subscribe to this mod's changes

post-merge is a skill published in the GitHub repository YoungjaeDev/my-claude-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 167 tokens to every session and 8,160 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

comet-github

A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.

rpamis/comet · 72 tokens

github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

zeenie-ai/OpenCompany · 51 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens

nvca-chart-release

Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.

NVIDIA/nvcf · 61 tokens