yeet

yeet is a skill for Claude Code, Codex from JHostalek/dotclaude. It costs 38 tokens per session (463 once invoked), scanned A, original, CC0-1.0.

A command for implementing requested work in the current code checkout, then opening and merging a pull request. A pull request is a proposed code change submitted for review and integration.

In plain words
What is it for?
It is for carrying out implementation tasks, running the required development checks, creating or updating a pull request, and optionally completing a full audit when invoked with the specified phrase.
Why use it?
It organizes coding, review, and integration into one workflow, with an optional audit that checks the completed work.

Skill for Claude CodeCodex

Part of the jhostalek-skills plugin — 32 skills, 12 agents shipped together

Install

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.

agentmods
npx agentmods add skills/jhostalek/dotclaude/yeet
Any agent
npx skills add JHostalek/dotclaude --skill yeet
Clone the repo
git clone --depth 1 https://github.com/JHostalek/dotclaude

Made for: Claude Code, Codex.

Or install jhostalek-skills, the plugin that ships this one along with the rest of its 32 skills, 12 agents.

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 yeet

README.md
[![agentmods](https://agentmods.dev/badge/skills/jhostalek/dotclaude/yeet.svg)](https://agentmods.dev/skills/jhostalek/dotclaude/yeet)
Your own site
<a href="https://agentmods.dev/skills/jhostalek/dotclaude/yeet"><img src="https://agentmods.dev/badge/skills/jhostalek/dotclaude/yeet.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 463 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00038 $0.00463
Opus 5 $0.00019 $0.00231
Sonnet 5 $0.00008 $0.00093
Haiku 4.5 $0.00004 $0.00046

Measured 5d ago against content hash aa1d063a5f09, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

yeet 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 5d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/resolve-skill-lib.mjs, scripts/resolve-skill.mjs, scripts/resolve-skill.test.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/yeet/SKILL.md · 22 lines

What it actually says

input = $ARGUMENTS

Set audit_requested only when input contains the standalone phrase with audit, case-insensitively. Remove that phrase from input; the remainder is work. If no work remains, stop and ask for it.

Complete this workflow in order:

  1. Before any remote, Git, or file mutation, run resolve-skill.mjs once from the task's working directory. Resolve mattpocock-skills:implement mattpocock-skills:tdd mattpocock-skills:code-review mattpocock-skills:setup-matt-pocock-skills jhostalek-skills:pr; append jhostalek-skills:audit only when audit_requested. Command: node <resolved-script-path> --cwd <task-cwd> <skills...>. Read every returned path completely and follow those instructions when invoked below. Treat unqualified skill references in a loaded plugin skill as belonging to that plugin's namespace. Stop before making changes if any requested dependency is missing, disabled, ambiguous, or unreadable.
  2. Work only in the current checkout. Never create, select, switch, sync, or remove worktrees or branches.
  3. Use mattpocock-skills:implement for the requested work.
  4. Use jhostalek-skills:pr to create or update the PR.
  5. When audit_requested, use jhostalek-skills:audit for a full audit, pragmatically fix every valid finding within scope, then use jhostalek-skills:pr again to push the fixes and update the PR. Otherwise skip this step.
  6. Merge the PR with the repository host's CLI and delete its remote source branch. Do not change the local checkout after merging.

Stop if a required skill, PR, check, or approval blocks the next step. Never bypass branch protection or failing required checks.

Report the merged PR and remote merge commit.

Files

What ships with it

4 files 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.

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. 5d ago First seen · 22 lines · 38 tokens per session scan A aa1d063a5f09

Subscribe to this mod's changes

yeet is a skill published in the GitHub repository JHostalek/dotclaude (11 stars, last pushed today), licensed CC0-1.0. It adds 38 tokens to every session and 463 once invoked, about $0.0002 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.