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 JimmyPaolini/codebase --skill create-pull-requestgit clone --depth 1 https://github.com/JimmyPaolini/codebaseWrote 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/jimmypaolini/codebase/create-pull-request)<a href="https://agentmods.dev/skills/jimmypaolini/codebase/create-pull-request"><img src="https://agentmods.dev/badge/skills/jimmypaolini/codebase/create-pull-request/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/jimmypaolini/codebase/create-pull-request"><img src="https://agentmods.dev/badge/skills/jimmypaolini/codebase/create-pull-request.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00044 | $0.04180 |
| Opus 5.5 | $0.00018 | $0.01672 |
| Sonnet 5.5 | $0.00009 | $0.00836 |
| Haiku 4.5 | $0.00004 | $0.00418 |
Grade A, and why
create-pull-request 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 — 520 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pull Request Conventions
This skill teaches how to create and manage pull requests for this codebase. Follow these conventions for consistent, reviewable PRs that pass CI validation.
When to Use This Skill
- Creating a new pull request
- Writing PR titles and descriptions
- Preparing changes for review
- Understanding PR workflows and requirements
- Linking PRs to issues
PR Title Format
PR titles must follow the same format as commit messages:
<type>(<scope>): <gitmoji> <subject>
Structure Rules
- Type: Required, lowercase, from allowed types
- Scope: Required, lowercase, from allowed scopes
- Gitmoji: Required, emoji at start of subject
- Subject: Required, lowercase, imperative mood, no period
Valid Types
| Type | Description |
|---|---|
feat |
A new feature or capability that adds value for users |
fix |
A bug fix that addresses a specific issue or problem |
docs |
Documentation, AGENTS.md, SKILL.md, README, and planning files |
test |
Adding or correcting unit, integration, or end-to-end tests |
refactor |
Code restructuring that neither fixes a bug nor adds a feature |
style |
Formatting, whitespace, or code structure changes with no semantic effect |
perf |
A code change that improves performance (caching, query optimization, etc.) |
chore |
Housekeeping that doesn't modify src or test files (gitignore, editor config, etc.) |
ci |
GitHub Actions workflows, composite actions, and CI/CD scripts |
build |
Build system, Vite/Docker/Helm config, or external dependency integration |
revert |
Reverts a previous commit |
Valid Scopes
| Scope | Description |
|---|---|
ic-suite |
In-house code measurement and validation toolchains (Callidescope, Codependix, Codometer, Conformetry) and their shared conventions |
affirmations |
Python Jupyter notebook application for LangGraph affirmation generation |
caelundas |
Node.js CLI for astronomical calendar generation (NASA JPL ephemeris) |
configuration |
Workspace root config files (tsconfig, eslint, vitest, nx.json, etc.) |
conformetry |
Code generator templates and validation tests for generated instances |
dependencies |
Dependency version changes (upgrades, additions, removals via pnpm) |
deployments |
GitHub Actions workflows and CI/CD pipeline configuration |
documentation |
Markdown docs, skills, planning files, and AGENTS.md files |
infrastructure |
Helm charts, Terraform configs, and Kubernetes resources |
JimmyPaolini |
Static GitHub profile README project (markdown and assets) |
lexico |
TanStack Start SSR Latin dictionary web app with Supabase backend |
lexico-components |
Shared React/shadcn component library |
lexico-entities |
Shared TypeORM entities and GraphQL types |
lexico-ingestion |
Data ingestion scripts for Lexico |
meanderaw |
Greek meander (key/fret) SVG generator CLI and the composable motif/modifier library it reads |
sempientor |
Lexical gap discovery CLI that surveys English for morphological, phonotactic, and semantic gaps and coins words to fill them |
callidescope |
Call stack tracing and linting CLI, the configuration package it reads, and the packages that build and render its call graph |
codependix |
Dependency graph export CLI, the configuration package it reads, and the package that judges the graphs against declared rules |
codometer |
Code statistics measurement CLI, the configuration package it reads, and the packages that diff and render its pull request change report |
no-release |
Escape hatch: suppress semantic-release for any commit type |
release |
Version bumps and release commits generated by semantic-release |
reporting |
Pull request change report generation and the packages that diff and render it |
scripts |
Shell and TypeScript scripts in scripts/ (sync, setup, utilities) |
testing |
Vitest configuration, shared test utilities, and coverage setup |
synchronization |
Synchronization application and commands for automating workflows |
validation |
Validation CLI and the checks it runs, such as pull request metadata |
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 · +19 lines 53f77bf1ca33
- 25d ago Changed 0f5083dfa474
- 26d ago Changed · +1 lines 69d63bea43d8
- 1mo ago Changed · -1 lines cd7703bf7851
- 1mo ago Changed b5d0d4b4a47c
- 1mo ago First seen · 501 lines · 44 tokens per session scan A 30e8f4a77abc
create-pull-request is a skill published in the GitHub repository JimmyPaolini/codebase (0 stars, last pushed 19d ago), licensed MIT. It adds 44 tokens to every session and 4,180 once invoked, about $0.0002 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 2026-09-01.
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.
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.
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.
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…
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.