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/paulbaranowski/wild-horses/plan-splitnpx skills add paulbaranowski/wild-horses --skill plan-splitgit clone --depth 1 https://github.com/paulbaranowski/wild-horsesWrote 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/paulbaranowski/wild-horses/plan-split)<a href="https://agentmods.dev/skills/paulbaranowski/wild-horses/plan-split"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/plan-split.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 | $0.00071 | $0.02894 |
| Opus 5 | $0.00036 | $0.01447 |
| Sonnet 5 | $0.00014 | $0.00579 |
| Haiku 4.5 | $0.00007 | $0.00289 |
Grade A, and why
plan-split 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.
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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plan-split
Decompose one plan into N child implementation-task plans under ~/plans/<repo>/, each a thin vertical slice (tracer bullet), wired together with plan-keeper's native Blocked-by: dependencies and staged at todo. Queue the staged slices through plan-crew (which stamps each one's Agent: tag — the dispatch gate file-meta set doesn't write) and groundcrew runs the wave in dependency order — the ready ones immediately, the blocked ones the moment their prerequisites finish.
This is the to-issues decomposition pattern retargeted from an external issue tracker to the plans tree. It composes the existing CLI (save, file-meta get, file-meta set) — there is no new subcommand.
Where this sits
plan-keeper's unit of work is a task, and every task is a plan file. A planning task spawns more plans; an implementation task produces code (see ../../README.md "The model"). plan-split is the bridge: it takes one source plan (a spec / design / exec-plan) and spawns its child implementation tasks, each ready for groundcrew. It does not file anything to Linear/Jira — that stays the occasional plan-linear / plan-jira export.
Quick reference
- Source plan: the single plan being decomposed. A saved file in
~/plans/<repo>/(named by path, topic, or "the plan I just saved") or the current conversation's plan. See Choosing the source. - Slice (child plan): one tracer-bullet plan written as
~/plans/<repo>/<date>-<project>-NN-<slice>--exec-plan.md,Kind: exec-plan,Status: todo. - Ordinal: each slice topic carries a zero-padded ordinal (
01,02, …) so the wave sorts in order inplan-list. - Dependencies: the native
Blocked-by:frontmatter field (comma-separated prerequisite ticket IDs). groundcrew holds atodoslice until every prerequisite isdone, then auto-dispatches. See ../../groundcrew/README.md "Dependencies between plans". - Provenance: each slice records a
Source:frontmatter key pointing at the source plan — provenance, not a dependency (keep it distinct fromBlocked-by:). - Source plan disposition: when it was a saved file, it is marked
doneafter slicing (its deliverable — the child plans — has been produced). <repo>: auto-derived or override — see ../../repo-derivation.md.- Approval gate: the breakdown is presented and iterated with the user; nothing is written until the user approves.
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.
- 5d ago First seen · 178 lines · 71 tokens per session scan A 4ac173cf9e82
plan-split is a skill published in the GitHub repository paulbaranowski/wild-horses (11 stars, last pushed 17d ago), licensed MIT. It adds 71 tokens to every session and 2,894 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…