test-and-merge

A developer-run process for testing a change, merging it with the latest main branch, opening a pull request, waiting for CI, and merging it when checks pass. CI means automated checks run by the repository.

In plain words
What is it for?
Use it after implementing a fix to run equivalence tests, update the branch, push it, create a pull request, monitor CI, and self-merge when approved.
Why use it?
It provides a repeatable path from a completed fix to a verified merge and identifies when conflicts require senior help.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/loopdive/js2/test-and-merge
Any agent
npx skills add loopdive/js2 --skill test-and-merge
Clone the repo
git clone --depth 1 https://github.com/loopdive/js2

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 501 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00043 $0.00501
Opus 5 $0.00022 $0.00251
Sonnet 5 $0.00009 $0.00100
Haiku 4.5 $0.00004 $0.00050

Measured 3d ago against content hash 369c776a2d76, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-and-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 3d 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.

.claude/skills/test-and-merge/SKILL.md · 58 lines

What it actually says

Test and Merge Pipeline

Devs run this themselves after implementing a fix. There is no separate tester agent — CI handles test262, and devs self-merge when CI passes.

Step 1: Merge main into branch

cd /workspace/.claude/worktrees/<branch>
git fetch origin && git merge origin/main
  • Clean merge: proceed
  • Conflicts in dashboard/, plan/, public/: git checkout --theirs <file>, then pnpm run build:planning-artifacts
  • Conflicts in src/**/*.ts: create [CONFLICT] task in TaskList for senior-developer. STOP.

Step 2: Run equivalence tests

npm test -- tests/equivalence.test.ts

All equivalence tests must pass. Any new failure = regression, fix before pushing.

Step 3: Push and open PR

git push origin <branch>
gh pr create --base main --title "fix(#N): <description>" --body "..."

Step 4: Wait for CI

Use a foreground blocking loop — keeps the agent occupied until CI result lands:

until [ -f /workspace/.claude/ci-status/pr-<N>.json ] && \
  [ "$(jq -r '.head_sha' /workspace/.claude/ci-status/pr-<N>.json)" = "$(git rev-parse HEAD)" ]; \
  do sleep 60; done

Step 5: Self-merge via /dev-self-merge

Run /dev-self-merge <N> — outputs MERGE or ESCALATE.

  • MERGE: gh pr merge <N> --merge --admin
  • ESCALATE: message tech lead with criterion, values, PR number

Step 6: Post-merge cleanup

  1. git worktree remove /workspace/.claude/worktrees/<branch>
  2. TaskUpdate(status: completed)
  3. TaskList → claim next task, or shut down if queue is empty
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. 3d ago First seen · 58 lines · 43 tokens per session scan A 369c776a2d76

Subscribe to this mod's changes

test-and-merge is a skill published in the GitHub repository loopdive/js2 (59 stars, last pushed 3d ago), licensed Apache-2.0. It adds 43 tokens to every session and 501 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.