agent-toolkit: Skill for Claude Code

.agents/skills/ox-pr-header/SKILL.md

ox-pr-header is a skill for Claude Code, Codex from sageox/agent-toolkit. It costs 140 tokens per session (1,039 once invoked), scanned A, a copy of ox-cli-pr-header, Apache-2.0.

A command that creates a credit line for a pull request, which is a proposed code change submitted for review.

In plain words
What is it for?
Use it when creating a pull request that was shaped by SageOx team context, then place the generated line at the top of the description.
Why use it?
It avoids hand-writing markup that may display incorrectly and prevents crediting SageOx when it did not influence the work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is sageox/agent-toolkit's own configuration. It tells Claude Code and Codex how to work on agent-toolkit 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 agent-toolkit configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sageox/agent-toolkit. 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/sageox/agent-toolkit/main/.agents/skills/ox-pr-header/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sageox/agent-toolkit

Made for: Claude Code, 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 ox-pr-header

README.md
[![agentmods](https://agentmods.dev/badge/skills/sageox/agent-toolkit/ox-pr-header/github.svg)](https://agentmods.dev/skills/sageox/agent-toolkit/ox-pr-header)
Your own site
<a href="https://agentmods.dev/skills/sageox/agent-toolkit/ox-pr-header"><img src="https://agentmods.dev/badge/skills/sageox/agent-toolkit/ox-pr-header/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 ox-pr-header

Your own site · 80×15
<a href="https://agentmods.dev/skills/sageox/agent-toolkit/ox-pr-header"><img src="https://agentmods.dev/badge/skills/sageox/agent-toolkit/ox-pr-header.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,039 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 94% copy Near-identical to another mod 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 $0.00140 $0.01039
Opus 5 $0.00070 $0.00519
Sonnet 5 $0.00028 $0.00208
Haiku 4.5 $0.00014 $0.00104

Measured yesterday against content hash 47113031b1f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ox-pr-header 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 yesterday.

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.

Origin

This is a copy

94% identical to ox-cli-pr-header — 98 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/ox-pr-header/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You do not hand-write this markup — ox pr header does. A GitHub PR body is sanitized harder than repo markdown (no CSS, no styled tables); the line is built from the exact primitives that survive (<picture> wordmark, <a> links, <sub> caption). Hand-authoring it is how it silently renders as a bordered table or a vanished wordmark. Run the command and paste its output verbatim.

When

At PR-creation time, only when SageOx-delivered team context measurably shaped the work (your contribution score is not none). If SageOx did not shape it, omit both the header and the SageOx-Session: trailer — publishing SageOx credit for work it did not influence is the fabrication #809 guards against. When it did shape the work, the header is the top of the body and the SageOx-Session: trailer stays the last line (they serve different readers: the header a human, the trailer the reconciler).

How

  1. Gather what the PR credits (you already hold this from your session):

    • the plan ids you saved (pln_…), if any;
    • the enrichment counts from ox plan enrich (related sessions / concurrent edits), if any.
  2. Run the command — the current session is auto-linked; add plans + enrichment:

    ox pr header \
      --plan pln_4d8e2f --plan pln_1a6b9c \
      --prior-art 2 --collisions 1
    

    --session <url|ses_id> adds/overrides sessions (default: the live session). --no-stat drops the whisper. --style text|image|auto follows ox config (pr_visuals.style) by default. --json returns the markup plus resolved inputs for verification.

  3. Paste the output as the FIRST lines of the PR body, above your summary. Write the body via a file, never a heredoc — a heredoc mangles the markup:

    ox pr header > body.md
    printf '\n' >> body.md
    cat description.md >> body.md   # your written summary
    # ...keep the SageOx-Session: trailer as the last line...
    gh pr create --body-file body.md
    

Read the full file on GitHub · 81 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. yesterday First seen · 81 lines · 140 tokens per session scan A 47113031b1f2

Subscribe to this mod's changes

ox-pr-header is a skill published in the GitHub repository sageox/agent-toolkit (10 stars, last pushed today), licensed Apache-2.0. It adds 140 tokens to every session and 1,039 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to ox-cli-pr-header, differing in 98 lines, and is treated as a copy.