Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add tomzx/agents --skill create-prgit clone --depth 1 https://github.com/tomzx/agentsWrote 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.
[](https://agentmods.dev/skills/tomzx/agents/create-pr)<a href="https://agentmods.dev/skills/tomzx/agents/create-pr"><img src="https://agentmods.dev/badge/skills/tomzx/agents/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.
<a href="https://agentmods.dev/skills/tomzx/agents/create-pr"><img src="https://agentmods.dev/badge/skills/tomzx/agents/create-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
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 →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 140 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00101 | $0.04920 |
| Opus 5.5 | $0.00040 | $0.01968 |
| Sonnet 5.5 | $0.00020 | $0.00984 |
| Haiku 4.5 | $0.00010 | $0.00492 |
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 20d 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.
How it starts
The opening of the file, as written. The whole thing — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Pull Request
Opens a GitHub pull request for the current branch with a structured description that maps implementation changes to acceptance criteria, links the originating issue, and requests reviewers.
Whether the PR is created on GitHub (and visual-proof assets uploaded, reviewers assigned) is decided by should-post-to-github (based on ~/.sdlc/config.yaml); when posting is disabled it drafts the description and shows it for review instead.
It is a pure consumer of visual proof: it reads the manifest written by /validate-implementation and embeds any captured asset inline so reviewers see proof the moment the PR opens.
It does not capture recordings itself; recording happens at human-review time, before the PR exists.
It also surfaces the design decisions the implementation made: recorded ADRs are pulled from .sdlc/knowledge/decisions/, and ad-hoc choices made while implementing are summarized, both in a Design decisions section (moved to a follow-up PR comment when the description would grow too large).
After creation it posts a few inline context comments via ghx where the diff is not self-explanatory, so reviewers do not have to reverse-engineer the change.
Prerequisites
- Apply the shared SDLC conventions in
skills/sdlc/references/shared.md. - If no argument is provided, use
$REPOand link$ISSUE_NUMBER. ghCLI authenticated with write access to the target repository- Current branch has commits not on the base branch
- A related GitHub issue number (strongly recommended; omit only for housekeeping PRs)
- All CI checks (lint, typecheck, tests, build) passing locally before the PR is opened, so CI is not the first to report a break
- For visual proof (captured beforehand): run
/validate-implementationon the branch first. It records a CLI demo (via/record-asciinema) or a web screenshot (via/record-playwright) and writes$PROOF_DIR/captured-proof.json. If that manifest is absent,create-promits the Visual proof section and suggests running/validate-implementationfirst (it never captures on its own).
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.
- 20d ago Changed · +7 lines 631c3cb91569
- 21d ago Changed · +4 lines cfa5ce73355f
- 22d ago Changed · -1 lines 1b1122e2739f
- 24d ago Changed d065602ec4a9
- 27d ago Changed 7b2f236b1f74
- 28d ago Changed · +4 lines a537b18ade11
- 1mo ago Changed · +87 lines · +8 tokens per session cdacce9b18fb
- 1mo ago Changed · -1 lines 4e8c0c774d2f
- 2mo ago First seen · 302 lines · 93 tokens per session scan A 6f83c91ad7c4
create-pr is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 101 tokens to every session and 4,920 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
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.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
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.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
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…