okfmem: Skill for Claude Code

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

revise-pr is a skill for Claude Code from s-annam/okfmem. It costs 111 tokens per session (3,716 once invoked), scanned A, original, Apache-2.0.

A workflow for updating a GitHub pull request after reviewers leave comments. It checks out the request's branch, addresses each unresolved discussion, and reports why any requested change is not made.

In plain words
What is it for?
Use it to respond to review feedback on a specific pull request. It makes the fixes, runs checks, pushes one update, then replies to and resolves the relevant discussions.
Why use it?
It keeps review replies, code changes, tests, and discussion resolution together. This helps avoid losing approvals when a new push makes reviews stale.

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 # HARD — must exit 0 before any push.

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/revise-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 revise-pr

README.md
[![agentmods](https://agentmods.dev/badge/skills/s-annam/okfmem/revise-pr/github.svg)](https://agentmods.dev/skills/s-annam/okfmem/revise-pr)
Your own site
<a href="https://agentmods.dev/skills/s-annam/okfmem/revise-pr"><img src="https://agentmods.dev/badge/skills/s-annam/okfmem/revise-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 revise-pr

Your own site · 80×15
<a href="https://agentmods.dev/skills/s-annam/okfmem/revise-pr"><img src="https://agentmods.dev/badge/skills/s-annam/okfmem/revise-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,716 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 $0.00111 $0.03716
Opus 5 $0.00056 $0.01858
Sonnet 5 $0.00022 $0.00743
Haiku 4.5 $0.00011 $0.00372

Measured 9d ago against content hash d4a7481d22df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

revise-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.

.claude/skills/revise-pr/SKILL.md · 309 lines

How it starts

The opening of the file, as written. The whole thing — 309 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Revise PR

Take a PR from "reviewer left feedback" to "all threads answered and the branch updated": check out the PR branch → address each unresolved review thread in code (or reply with a rationale when it's out of scope) → run the leak gate + checks → commit + push to the PR branch → reply to each thread and resolve the ones you actually fixed.

This is the mirror of open-pr: that skill gets a change to review; this one closes the loop after review.

Input

Parse the argument for a PR number (12, #12) and optionally --repo owner/repo. If no PR number is given, infer it from the current branch:

gh pr view --json number,headRefName,state -q '{n:.number,head:.headRefName,state:.state}'

If that finds no PR for the current branch and none was passed, list open PRs and ask which one. Never guess.

Why this skill exists

main is protected with dismiss-stale-reviews-on-push: pushing new commits to a PR branch dismisses any existing approval. So the order matters — address everything in one pass, push once, then re-request review. This skill encodes that order so a contributor doesn't push piecemeal and burn approvals, and so every thread gets a visible reply (the PR-author signal norm: don't push silent).

(While the repo is solo, the owner can't approve their own PR — GitHub blocks self-approval — so the owner merges via admin bypass once verify is green. The dismiss-on-push still applies to any Code Owner review a contributor's PR earned.)

Process

Step 0: Detect repo + PR

REPO="$(gh repo view --json nameWithOwner -q .nameWithOwner)"   # s-annam/okfmem
OWNER="${REPO%%/*}"; NAME="${REPO##*/}"
# PR_NUM from the argument, or inferred from the current branch (see Input).
gh pr view "$PR_NUM" --repo "$REPO" \
  --json number,title,state,headRefName,baseRefName -q '{n:.number,t:.title,s:.state,h:.headRefName,b:.baseRefName}'

If the PR is not OPEN, stop and say so.

Step 1: Get onto the PR branch (clean tree)

Read the full file on GitHub · 309 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. 9d ago First seen · 309 lines · 111 tokens per session scan A d4a7481d22df

Subscribe to this mod's changes

revise-pr is a skill published in the GitHub repository s-annam/okfmem (5 stars, last pushed 26d ago), licensed Apache-2.0. It adds 111 tokens to every session and 3,716 once invoked, about $0.0006 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

review-implement-phase

Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.

prisma/orm · 38 tokens

engram-branch-pr

PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.

Gentleman-Programming/engram · 37 tokens

verify-behavior

Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…

nicknisi/dotfiles · 68 tokens

github-contributor

End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…

daymade/claude-code-skills · 133 tokens

revdiff

Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…

umputun/revdiff · 248 tokens

write-pr

Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.

tldraw/tldraw · 53 tokens