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 sergeyklay/.agents --skill create-prgit clone --depth 1 https://github.com/sergeyklay/.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/sergeyklay/.agents/create-pr)<a href="https://agentmods.dev/skills/sergeyklay/.agents/create-pr"><img src="https://agentmods.dev/badge/skills/sergeyklay/.agents/create-pr.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00054 | $0.01331 |
| Opus 5 | $0.00027 | $0.00665 |
| Sonnet 5 | $0.00011 | $0.00266 |
| Haiku 4.5 | $0.00005 | $0.00133 |
Grade A, and why
create-pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating a Pull Request
Workflow
Step 1: Verify branch state
CURRENT=$(git branch --show-current)
DEFAULT=$(gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name')
- If
$CURRENTequals$DEFAULTor isdevelop/release/*/hotfix/*: inform user they are on a protected branch, cannot create PR from here - If uncommitted changes exist: commit first (use git-commit skill)
- If branch not pushed:
git push -u origin $CURRENT
Step 2: Analyze changes
DEFAULT=$(gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name')
git log --format="%s%n%b" "$DEFAULT..HEAD"
git diff --name-only "$DEFAULT..HEAD"
git diff --stat "$DEFAULT..HEAD"
From the diff and commits, identify:
- Type: primary change type (feat, fix, refactor, chore, perf)
- Intent: business/technical goal (1-2 sentences)
- Entry point: most critical changed file for reviewer
- Sensitive areas: files needing extra scrutiny (auth, payments, data)
- Breaking changes:
!in commits or BREAKING CHANGE footer - Migrations: database or schema changes
Step 3: Generate title
Conventional Commits format: <type>[scope]: <description>
- Imperative mood, under 72 chars, no period, English only
- Match the project's commit style (check
git log --format="%s" -20)
NEVER add task ID, issue number, or other metadata to the title:
❌ Wrong:
feat(messages): add server-only synthetic mailbox archive parser (BP-1234)
✅ Correct:
feat(messages): add server-only synthetic mailbox archive parser
Step 4: Generate description
Use the template from assets/pull_request_template.md. Three sections:
- Scope & Context - Type, Intent, Related Issues
- Reviewer Guide - Complexity (Low/Medium/High), Entry Point, Sensitive Areas
- Risk Assessment - Breaking Changes, Migrations/State
Formatting rules:
- No fluff intros ("This PR updates...")
- Filenames in backticks: `path/to/file.ts`
- Use " - " (hyphen), not "-" (em-dash)
- No hard-wrap in body prose: GitHub renders soft line breaks as
<br>in PR descriptions, so wrapping at ~80 chars creates visible artificial breaks. Let paragraphs flow; break only for new paragraphs, list items, or code blocks - All sections required, sub-sections only when relevant data exists
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 131 lines · 54 tokens per session scan A da29b2b9b10d
create-pr is a skill published in the GitHub repository sergeyklay/.agents (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 1,331 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.
Other skills, from other repositories
git-commit-helper
Generate conventional commit messages automatically. Use when user runs git commit, stages changes, or asks for commit message help. Analyzes git diff to create clear, descriptive conventional commit messages. Triggers on git commit, staged changes, commit message requests.
dpf-worktree-per-session
Use when starting, entering, auditing, or managing a concurrent DPF coding session that touches the working tree.
dpf-pr-with-dco
Use when ready to open a DPF pull request.
dpf-local-merge-ci-before-push
Use before pushing or opening a DPF PR when a branch needs local merged-code verification.
draft-kernel-edit-pr
Draft a GitHub pull request that edits a founder-kernel page. Kernel pages under docs/founder-kernel/ are PR-only per spec §4 (never written by the runtime); this skill walks the user through reading the current markdown, applying the requested change, validating wikilinks + manifest counts, and opening a draft PR for…
vigilante-issue-implementation
Implement a GitHub issue end-to-end when Vigilante dispatches work for a watched repository. Use the provided worktree, respect repository instructions, comment on the issue as work progresses, and report failures back to GitHub.