yeet

yeet is a skill for Claude Code, Codex from macintog/codex-spine. It costs 63 tokens per session (514 once invoked), scanned A, original, MIT.

A controlled procedure for finishing a registered Git task after its checks have already passed. The word “yeet” is an explicit instruction to commit, publish or integrate the work, prove the result, and retire the task.

In plain words
What is it for?
It helps complete the final Git transaction for an approved task, including committing changes, publishing or integrating them, checking the live result, and updating task records.
Why use it?
It prevents unfinished, unregistered, or unverified work from being committed or published. It also avoids running extra tests or deployment steps as part of this final action.

Skill for Claude CodeCodex

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/macintog/codex-spine/yeet
Any agent
npx skills add macintog/codex-spine --skill yeet
Clone the repo
git clone --depth 1 https://github.com/macintog/codex-spine

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 yeet

README.md
[![agentmods](https://agentmods.dev/badge/skills/macintog/codex-spine/yeet.svg)](https://agentmods.dev/skills/macintog/codex-spine/yeet)
Your own site
<a href="https://agentmods.dev/skills/macintog/codex-spine/yeet"><img src="https://agentmods.dev/badge/skills/macintog/codex-spine/yeet.svg" alt="Measured on agentmods" height="20"></a>
Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 514 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 $0.00063 $0.00514
Opus 5 $0.00032 $0.00257
Sonnet 5 $0.00013 $0.00103
Haiku 4.5 $0.00006 $0.00051

Measured 3d ago against content hash c8c15fc42f51, 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 3d 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.

skills/yeet/SKILL.md · 41 lines

What it actually says

Yeet

validated registered task → commit → publish or integrate → prove → retire

Treat the operator's exact yeet instruction as authorization to attempt the registered task's configured terminal Git transaction now. It is not authority to run product tests, verification suites, bootstrap, hosting, deployment, release work, or to select additional integration refs.

  1. Read the repository's Git lane and bind the current checkout to exactly one active managed task. Refuse an unregistered, detached, dirty-adopted, or wrong-task-class checkout.
  2. Use the compact passing validation result already produced by the working thread, recorded as PASS: <checks and result>. If it is missing or failed, stop before mutation; do not manufacture it or run tests.
  3. Prepare the task's commit message, review title/body when ordinary, and the generation-checked checkpoint JSON model when the repository is adopted.
  4. Run codex-git-safe yeet --apply once with those inputs. Let the transaction stage the proven task delta, commit if needed, publish or integrate according to task class, prove the live remote state, update the checkpoint, re-home, and retire only the task-owned local state. When the task was isolated from an existing non-authoritative tracked review head, the transaction may update that same head only if both its tracking and live remote tips still equal the recorded isolation baseline; never create a replacement review.
  5. On a blocker, report the exact failed precondition and retained phase. A retry uses the same command and inputs. After retirement, use --task only to re-prove the recorded terminal result.

Success requires the task-class-specific remote proof, checkpoint disposition, and absence of its local worktree, branch, and active registration. Completion is terminal; do not ask for or emit a second closeout phrase.

This packet deliberately recycles a familiar name for a materially different Git contract. When comparing it with public skills named yeet, read Same name, different contract.

Files

What ships with it

2 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. 3d ago First seen · 41 lines · 63 tokens per session scan A c8c15fc42f51

Subscribe to this mod's changes

yeet is a skill published in the GitHub repository macintog/codex-spine (9 stars, last pushed 4d ago), licensed MIT. It adds 63 tokens to every session and 514 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.

Related

Other skills, from other repositories

apm-issue-autopilot

Use this skill to drive any open microsoft/apm issue (bug, feature, docs, refactor, perf) from raw intake to a mergeable PR with triage as the central, paramount gate. Run the apm-triage-panel rubric per issue first, then present ONE consolidated triage review for the whole batch and escalate to the maintainer BY…

microsoft/apm · 238 tokens

bensz-rmd-rules

规范 AI 开发 R Markdown 分析脚本的行为准则。当用户要求"写 Rmd 分析"、"开发 R 脚本"、"做数据分析"时触发。核心原则:遵循主业与副业分离架构(.R 保留完整数据,.Rmd 应用业务阈值),优先使用用户已有 R 包资源;图表默认按 Nature 级别可读性与出版质量生成;专家级解读兼顾弱背景读者,提供四层框架、指标导读与不常用指标首次解释协议;路径验证确保跨平台兼容性。前提:luckyBase 为硬依赖。.

huangwb8/skills · 157 tokens

auto-test-project

当用户明确要求"测试项目"、"运行 auto-test-project"或"进行项目级测试"时使用。对完整项目进行多轮 A 轮批判性测试 + B 轮质量检查,系统化发现、记录、修复问题。⚠️ 不适用:用户只是想优化功能(应直接修改)、只是询问项目问题(应直接回答)、没有明确"测试"意图。.

huangwb8/skills · 94 tokens

auto-test-skill

当用户明确要求"测试技能"、"运行 auto-test"或"进行批判性测试"时使用。通过多轮 A 轮批判性测试 + B 轮质量原则检查,系统化发现、记录、修复问题,并沉淀可追溯的 .bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/auto-test-skill/output/plans/ 与 .bensz-api/task-{yyyymmdd-hhmm}-{简短描述}/auto-test-skill/output/tests/ 文档。⚠️ 不适用:用户只是想优化功能(应直接修改)、只是询问技能问题(应直接回答)、没有明确"测试"意图。.

huangwb8/skills · 158 tokens

brainstorming

当用户明确要求"使用 brainstorming"或"使用 awesome-code"时使用。⚠️ 不适用:用户只是想优化/改进某个功能(应直接修改)、只是询问技能问题(应直接回答)、没有明确使用 brainstorming/awesome-code 的一般性开发。.

huangwb8/skills · 65 tokens

context-optimizer

上下文优化专家。专注于长对话中的上下文管理、token 效率和性能优化。解决 lost-in-middle、context poisoning 等问题,提升 AI 代理在复杂任务中的表现。.

huangwb8/skills · 48 tokens