harn: Skill for Codex

.codex/skills/pr-finish-pass/SKILL.md

pr-finish-pass is a skill for Codex from burin-labs/harn. It costs 179 tokens per session (3,908 once invoked), scanned A, original, Apache-2.0.

A final review and cleanup pass for a pull request or feature branch before the change is merged. A pull request is a proposed code change awaiting review.

In plain words
What is it for?
Use it before opening or merging a pull request, or to polish an unpushed branch; it can rebase on the main branch, run CI, inspect the diff, and stop if there is no relevant work.
Why use it?
It catches the issues that can remain after a feature works, including correctness, performance, security, reliability, test, and code-quality problems, while also handling the listed rebase and CI steps.

Skill for Codex

Written for Codex: installed under .codex/. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is burin-labs/harn's own configuration. It tells Codex how to work on harn 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 harn configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./scripts/cargo_with_worktree_build_dir.sh nextest run -p <crate>.

Reuse

Borrowing it

Nothing to install: this file belongs to burin-labs/harn. 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/burin-labs/harn/main/.codex/skills/pr-finish-pass/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/burin-labs/harn

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 pr-finish-pass

README.md
[![agentmods](https://agentmods.dev/badge/skills/burin-labs/harn/pr-finish-pass/github.svg)](https://agentmods.dev/skills/burin-labs/harn/pr-finish-pass)
Your own site
<a href="https://agentmods.dev/skills/burin-labs/harn/pr-finish-pass"><img src="https://agentmods.dev/badge/skills/burin-labs/harn/pr-finish-pass/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 pr-finish-pass

Your own site · 80×15
<a href="https://agentmods.dev/skills/burin-labs/harn/pr-finish-pass"><img src="https://agentmods.dev/badge/skills/burin-labs/harn/pr-finish-pass.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 179 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,908 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 warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 74
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • high Tool Misuse · line 342
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 $0.00179 $0.03908
Opus 5 $0.00089 $0.01954
Sonnet 5 $0.00036 $0.00782
Haiku 4.5 $0.00018 $0.00391

Measured 11d ago against content hash 3353a0d5b95e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pr-finish-pass 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 11d 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.

.codex/skills/pr-finish-pass/SKILL.md · 380 lines

How it starts

The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pr-finish-pass

Final-polish sweep on whatever work is currently in flight. That is usually a named PR, but it works equally well on an unpushed feature branch or a session's accumulated diff. The goal is to get the change to a state a senior reviewer would land without comments.

The sweep is not a generic code review. It targets the recurring issues this repo accumulates between "the feature works" and "the PR is landable."

When to use

  • A PR is open and you want it merged today.
  • A feature branch is about to become a PR.
  • A session produced a diff worth landing and you want it polished before opening the PR.

If there is no current branch worth polishing — say so and stop.

Phase 0 — identify the work

Determine the scope before touching anything:

git status --short
git rev-parse --abbrev-ref HEAD                    # current branch
git log --oneline origin/main..HEAD                # commits to ship
gh pr view --json number,state,headRefName,mergeStateStatus 2>/dev/null

If gh pr view returns a PR, you are in PR mode. Otherwise you are in branch mode — the rebase / CI phases are skipped and you go straight to the review sweep.

Read the full diff before doing anything else:

git diff origin/main...HEAD

For PRs in PR mode, also read gh pr view --json title,body,comments and skim review comments — sometimes the easiest finding is one a reviewer already left.

Phase 1 — rebase on origin/main (PR mode only)

git fetch origin main
git rebase origin/main

Resolve conflicts inline. Common conflict rules in this repo:

  • changelog.d/*.md: keep distinct fragments from both sides. Release tooling owns the generated CHANGELOG.md.
  • docs/theme/harn-keywords.js: regenerate with make gen-highlight.
  • spec/HARN_SPEC.md / docs/src/language-spec.md: keep neither generated side. Resolve the editable spec/chapters/*.md sources, then run make sync-language-spec.
  • Cargo.lock: resolve from the merged manifests, then run make setup-rust in the worktree.
  • Any file with both sides reformatted: take one side then make fmt / make fmt-harn / portal lint as appropriate.

Read the full file on GitHub · 380 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. 11d ago First seen · 380 lines · 179 tokens per session scan A 3353a0d5b95e

Subscribe to this mod's changes

pr-finish-pass is a skill published in the GitHub repository burin-labs/harn (21 stars, last pushed yesterday), licensed Apache-2.0. It adds 179 tokens to every session and 3,908 once invoked, about $0.0009 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.

Related

Other skills, from other repositories

commit

Auto-fix, lint, test, and commit changes with a conventional commit message.

phel-lang/phel-lang · 16 tokens

archestra-pr-hygiene

Use when opening or updating an Archestra pull request to write an accurate conventional title and a practical, evidence-based description.

archestra-ai/archestra · 31 tokens

hunk-extensions

Maps the hunkdiff/extension authoring surface for Hunk, the terminal diff viewer — hiding or reordering reviewed files, docked panes, alternate file views, commands and key bindings, dialogs, workspace writes, themes, syntax languages, VCS backends, lifecycle events. Use when writing, debugging, or installing a Hunk…

modem-dev/hunk · 105 tokens

hunk-launch-video

Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.

modem-dev/hunk · 60 tokens

hunk-release

Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.

modem-dev/hunk · 38 tokens

hunk-review

Interacts with live Hunk diff review sessions via CLI. Inspects review focus, navigates files, hunks, and exact lines, reloads session contents, adds inline review comments, and paints attention marks on character ranges. Use when the user has a Hunk session running or wants to review diffs interactively.

modem-dev/hunk · 69 tokens