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 agentmods add skills/macintog/codex-spine/yeetnpx skills add macintog/codex-spine --skill yeetgit clone --depth 1 https://github.com/macintog/codex-spineWrote 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/macintog/codex-spine/yeet)<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>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 | $0.00063 | $0.00514 |
| Opus 5 | $0.00032 | $0.00257 |
| Sonnet 5 | $0.00013 | $0.00103 |
| Haiku 4.5 | $0.00006 | $0.00051 |
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.
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.
- 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.
- 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. - Prepare the task's commit message, review title/body when ordinary, and the generation-checked checkpoint JSON model when the repository is adopted.
- Run
codex-git-safe yeet --applyonce 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. - On a blocker, report the exact failed precondition and retained phase. A
retry uses the same command and inputs. After retirement, use
--taskonly 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.
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.
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.
- 3d ago First seen · 41 lines · 63 tokens per session scan A c8c15fc42f51
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.
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…
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。.
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。.
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。.
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。.
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。.