bedrock: Skill for Codex

.agents/skills/create-pr/SKILL.md

create-pr is a skill for Codex from christopher-buss/bedrock. It costs 47 tokens per session (1,006 once invoked), scanned A, original, MIT.

A GitHub pull-request workflow for opening a review request from an already committed and pushed branch. A pull request lets teammates inspect and discuss changes before they are merged.

In plain words
What is it for?
Use it to inspect a branch, identify referenced issues, and create a pull request with a conventional title and useful body.
Why use it?
It prevents accidental commits, pushes, or branch changes while checking that the branch and working tree are ready. It also builds the title and description from the actual code changes.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions CLAUDE.md; mentions Claude Code; installed under .agents/ (shared by several agents).

This is christopher-buss/bedrock's own configuration. It tells Codex how to work on bedrock itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything bedrock configures →

Reuse

Borrowing it

Nothing to install: this file belongs to christopher-buss/bedrock. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/christopher-buss/bedrock/main/.agents/skills/create-pr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/christopher-buss/bedrock

Made for: Codex.

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 create-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/christopher-buss/bedrock/create-pr/github.svg)](https://agentmods.dev/skills/christopher-buss/bedrock/create-pr)
Your own site
<a href="https://agentmods.dev/skills/christopher-buss/bedrock/create-pr"><img src="https://agentmods.dev/badge/skills/christopher-buss/bedrock/create-pr/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 create-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/christopher-buss/bedrock/create-pr"><img src="https://agentmods.dev/badge/skills/christopher-buss/bedrock/create-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,006 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00047 $0.01006
Opus 5.5 $0.00019 $0.00402
Sonnet 5.5 $0.00009 $0.00201
Haiku 4.5 $0.00005 $0.00101

Measured 5d ago against content hash 5f9ffa6b4ba1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-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 5d 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.

.agents/skills/create-pr/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Open a pull request for the current work, branching, committing, and pushing first if needed. Invoking this skill authorizes those steps: do them directly, without asking.

1. Get to a pushable feature branch

  1. On the default branch (gh repo view --json defaultBranchRef -q .defaultBranchRef.name)? Switch to a new type/short-description branch.
  2. Commit any uncommitted changes. Touched a versioned package? Record a change intent with pnpm change first (see "Releases" in CLAUDE.md).
  3. git push -u origin HEAD.

Stop and ask if the tree mixes unrelated edits or the push needs force.

Done when HEAD is a feature branch, the tree is clean, and the branch is on the remote.

2. Read the diff

git diff <base>...HEAD --name-status
git log <base>...HEAD --oneline
git diff <base>...HEAD

Capture every issue the commits reference (#NNN, closes #NNN, fixes #NNN).

Done when you can name the change type, the systems touched, and every referenced issue.

3. Title

type(scope): imperative description

Conventional commit, derived from the diff, not the branch name. Follow the PR-title rules in CLAUDE.md (lower-case subject, scope-enum, consumer-useful subject). Issue references belong in the body, not the title.

The title becomes the changelog entry, so name the payoff a reader cares about rather than the mechanism:

BAD

❌ perf(server): negotiate permessage-deflate on the websocket

GOOD

✅ perf(server): cut websocket frame size by 70%+ with gzipping

4. Body

Call the Skill tool with "pr" for the body template. Write the body for a reviewer who has not read the conversation, applying these repository rules to its sections:

  • Summary: open with the problem in one line, in the user's framing, before the view.
  • Evidence: name the command or artifact and the revision it covers. Show the exact test that fails before and passes after. Never restate suite-wide test, coverage, or lint results; CI owns those.
  • Merge Danger: for a one-way door, state the rollback condition, such as a coordinated consumer change or a migrated state file. Blast radius names the affected packages, commands, config, or state.

Read the full file on GitHub · 99 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. 5d ago Changed · -41 lines 5f9ffa6b4ba1
  2. 1mo ago Changed · +72 lines · +7 tokens per session 63d625c3aeb7
  3. 1mo ago First seen · 68 lines · 40 tokens per session scan A 168a61a93f2c

Subscribe to this mod's changes

create-pr is a skill published in the GitHub repository christopher-buss/bedrock (19 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 1,006 once invoked, about $0.0002 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 2026-09-01.

Related

Other skills, from other repositories

upstream-patches

Create, amend, remove, and rebase patches for Terraform provider submodules using ./scripts/upstream.sh. Use when upgrade-provider or manual patch work needs owning-patch lookup, patch conflict fixes, patch/hunk removal, or upstream rebase.

pulumi/agent-skills · 58 tokens

apex-github-operations

WORKFLOW SKILL — Scoped Git/GitHub operations: branches, commits, push, issues, PRs, Actions, releases. WHEN: "commit", "push", "open PR", "create branch", "create issue", "cut release", "GitHub operation". Uses git/gh CLI first; discover MCP only for unavailable CLI capabilities. DO NOT USE FOR: Azure deployment or…

jonathan-vella/apex-accelerator · 96 tokens

infra-as-code

Manage infrastructure in version control so it's reviewable, reproducible, and rollback-able. Invoke when provisioning new infra or cleaning up ad-hoc resources.

orlando-japan/claude-code-setting · 34 tokens

merge-batch

Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.

diegosouzapw/OmniRoute · 46 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