okfmem: Skill for Claude Code

.claude/skills/open-pr/SKILL.md

open-pr is a skill for Claude Code from s-annam/okfmem. It costs 66 tokens per session (2,885 once invoked), scanned A, original, Apache-2.0.

A workflow for turning a completed code change into a GitHub pull request, which is a proposed change submitted for review. It can create a branch, commit and push the changes, and fill in the pull request details.

In plain words
What is it for?
Use it when you want to open a pull request from the current work. It handles branching, committing, checks, pushing, and pull request creation.
Why use it?
It removes the repeated setup work involved in preparing a change for review and links the request to its issue when possible.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; mentions subagents.

This is s-annam/okfmem's own configuration. It tells Claude Code how to work on okfmem 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 okfmem configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/check-leaks.py # must exit 0.

Reuse

Borrowing it

Nothing to install: this file belongs to s-annam/okfmem. 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/s-annam/okfmem/main/.claude/skills/open-pr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/s-annam/okfmem

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.

agentmods badge for open-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/s-annam/okfmem/open-pr.svg)](https://agentmods.dev/skills/s-annam/okfmem/open-pr)
Your own site
<a href="https://agentmods.dev/skills/s-annam/okfmem/open-pr"><img src="https://agentmods.dev/badge/skills/s-annam/okfmem/open-pr.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,885 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.
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 $0.00066 $0.02885
Opus 5 $0.00033 $0.01443
Sonnet 5 $0.00013 $0.00577
Haiku 4.5 $0.00007 $0.00288

Measured 6d ago against content hash cdd319bc29b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

open-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 6d 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/open-pr/SKILL.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Open PR

Take a change from working tree to an open pull request against main, in one skill: branch (if needed) → commit → leak-gate → push → create the PR with a filled body that links the issue.

Input

Parse the argument for an issue number (e.g. 5, #5), a short commit message, and optionally --base <ref> (overrides the BASE from Step 0). If the issue number is absent, recover it from the branch name (feat/...-issue-5, gh-5) or a Closes #N / Refs #N trailer in an existing commit. If still unknown, open the PR without an issue link and note that in the output — don't block on it.

Refs that arrive after the PR already exists. If the issue number only becomes known once the PR is open (e.g. discovered during review), don't leave the commit message stale — amend it: append the Closes #N / Refs #N trailer, leaving the rest of the message otherwise intact, and diff git log -1 --format=%B before and after the amend to confirm nothing else changed:

git log -1 --format=%B > /tmp/before.txt   # or a scratch path — compare before/after
git commit --amend
git log -1 --format=%B > /tmp/after.txt
diff /tmp/before.txt /tmp/after.txt        # expect only the added trailer line
git push --force-with-lease -u origin "$BRANCH"   # never bare `--force`

Then add the same ref to the PR body (Step 5) if it isn't there yet.

If a calling skill hands over provenance records ({stage, model, effort}), render them verbatim into the ## Provenance block (Step 5.5) — don't re-derive.

Why this skill exists

main is protected (server-side branch protection): every change merges through a PR with a green verify CI check, linear history, and 1 approving review from a Code Owner (.github/CODEOWNERS). This skill is the fast, correct path: it always works on a feature branch, never on main. (While the repo is solo, the owner can't approve their own PR — GitHub blocks self-approval — so the owner merges via admin bypass, enforce_admins being off. That bypass goes away the day a second maintainer exists; then the approval rule binds everyone.)

Read the full file on GitHub · 260 lines

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. 6d ago First seen · 260 lines · 66 tokens per session scan A cdd319bc29b7

Subscribe to this mod's changes

open-pr is a skill published in the GitHub repository s-annam/okfmem (5 stars, last pushed 23d ago), licensed Apache-2.0. It adds 66 tokens to every session and 2,885 once invoked, about $0.0003 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 2026-08-31.

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

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

changelog-composer

Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".

Mathews-Tom/armory · 67 tokens