agentmods.dev

jackin-merge-pr

jackin-merge-pr is a skill for Claude Code, Codex from jackin-project/jackin-dev. It costs 43 tokens per session (1,028 once invoked), scanned A, original, Apache-2.0.

A workflow skill for completing and merging a jackin roadmap item through a pull request. A pull request is a proposed code change reviewed before it is merged.

In plain words
What is it for?
It runs pre-merge checks, retires the roadmap item in the documentation, handles approved exceptions, and squash-merges the pull request.
Why use it?
It checks the change, required automated tests, project documentation, and authorization before merging, stopping when a required condition fails.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present.

Part of the jackin-dev plugin — 11 skills shipped together

not rated 3repo 7d ago A scan Socket: passSnyk: pass 43 tokens original Apache-2.0

Good fit It runs pre-merge checks, retires the roadmap item in the documentation, handles approved exceptions, and squash-merges the pull request.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jackin-project/jackin-dev/jackin-merge-pr
View source ↗ jackin-project/jackin-dev
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 jackin-project/jackin-dev --skill jackin-merge-pr
Clone the repo
git clone --depth 1 https://github.com/jackin-project/jackin-dev

Made for: Claude Code, Codex.

Or install jackin-dev, the plugin that ships this one along with the rest of its 11 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 jackin-merge-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/jackin-project/jackin-dev/jackin-merge-pr.svg)](https://agentmods.dev/skills/jackin-project/jackin-dev/jackin-merge-pr)
Your own site
<a href="https://agentmods.dev/skills/jackin-project/jackin-dev/jackin-merge-pr"><img src="https://agentmods.dev/badge/skills/jackin-project/jackin-dev/jackin-merge-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,028 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
  • Socket pass 13 Aug 2026
  • Snyk pass 13 Aug 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.01028
Opus 5 $0.00022 $0.00514
Sonnet 5 $0.00009 $0.00206
Haiku 4.5 $0.00004 $0.00103

Measured 9d ago against content hash 60d1c1c8de61, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

jackin-merge-pr 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 9d 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.

skills/jackin-merge-pr/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

jackin-merge-pr

Sequence the jackin❯ pre-merge gates fail-closed, retire the roadmap item into docs, then squash-merge. Reuses the .github/ agent rules (auto-loaded) and PULL_REQUESTS.md — sequences them, never restates them.

When to use

  • Operator runs jackin-merge-pr [<PR>] to merge a jackin❯ PR (defaults to the current branch's PR).

When NOT to use

  • Opening or iterating a PR → jackin-create-pr / jackin-propose.

Arguments

  • --no-poll — do not wait on pending CI; stop and report instead.
  • --admin <check> — authorize bypassing one named failing check (still needs the high-blast-radius confirm).

Red flags — STOP

  • No clear authorization for this PR and it is high-blast-radius → STOP, confirm first.
  • Any required CI check failing → STOP (no --admin bypass without --admin <check> + confirm).
  • Roadmap item not retired / not status-moved when the PR ships or advances it → STOP, fix first.

Process

  1. Resolve PR. Current branch's PR or the arg. Read gh pr view and gh pr diff.
  2. Blast-radius classify. High if the diff touches a versioned schema, auth/security surface, .github/workflows/**, or needs a force-push / --admin. High → pause for one explicit confirm. Normal → proceed (invoking the skill is the go).
  3. CI gate. gh pr checks <PR>: if pending, poll until green (unless --no-poll); if any check fails, STOP. Trust CI — which runs cargo xtask schema-check plus the test/clippy/fmt jobs — no local re-run.
  4. Roadmap retirement. Does this PR ship the last piece of its roadmap item?
    • Yes → [bin] cargo xtask roadmap retire <slug> --plan prints the worklist: the page content, every inbound link (grep <slug>), and the meta.json entry. [agent] Do the judgment moves — operator detail → guides//commands/, design detail → reference/, write the ## Completed bullet in roadmap/index.mdx, repoint inbound links; commit docs:. [bin] cargo xtask roadmap retire <slug> --apply removes the meta.json entry, deletes the .mdx, runs the audit, and fails if any inbound link still points at the dead slug. Run the bun docs gate; push.
    • Partial → cargo xtask roadmap retire <slug> --partial sets **Status**: Partially implemented and keeps the page; name the remaining phases; commit; push.
  5. Metadata reconcile. Title/body match the final diff? Squash writes the title verbatim into history. Fix via gh pr edit if stale; surface the change in your reply.
  6. Squash-merge. Build a body file (prose summary, no checklists), append trailers via cargo run -p jackin-pr-trailers -- --body-file, then gh pr merge <PR> --squash --body-file. Confirm the title carries (#N).
  7. Report. Merged SHA and what retirement did.

Read the full file on GitHub · 55 lines

Files

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.

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. 9d ago First seen · 55 lines · 43 tokens per session scan A 60d1c1c8de61

Subscribe to this mod's changes

jackin-merge-pr is a skill published in the GitHub repository jackin-project/jackin-dev (3 stars, last pushed 7d ago), licensed Apache-2.0. It adds 43 tokens to every session and 1,028 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.

Git and workflow
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

codex-autoresearch

Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…

leo-lilinxiao/codex-autoresearch · 80 tokens