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 pmatos/skills --skill pm-plangit clone --depth 1 https://github.com/pmatos/skillsWrote 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/pmatos/skills/pm-plan)<a href="https://agentmods.dev/skills/pmatos/skills/pm-plan"><img src="https://agentmods.dev/badge/skills/pmatos/skills/pm-plan.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 5.1 | $0.00093 | $0.03277 |
| Opus 5 | $0.00046 | $0.01639 |
| Sonnet 5 | $0.00019 | $0.00655 |
| Haiku 4.5 | $0.00009 | $0.00328 |
Grade C, and why
pm-plan scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
On the **shell path**, clean up the staging directory you created (`rm -rf "$PLAN_TMP"`). On the native path there is nothing to clean up. How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Implementation Planning (dual-harness)
This skill produces a validated, adversarially-reviewed implementation plan at .ultraplan/<plan-name>.md after exploring the codebase — without writing any production code. The workflow is identical whichever harness runs it. Only the mechanism for dispatching subagents (parallel exploration, plan naming, adversarial review) differs, and that mechanism is selected once, up front, in Determine your harness below.
Task
$ARGUMENTS
Determine your harness
Before dispatching any subagent, pick the dispatch mechanism that matches your capabilities. Branch on the capability, not on a product name:
- Native path — you have a native subagent tool (the
Agent/Tasktool), e.g. you are Claude Code. Readreferences/dispatch-claude.mdand spawn read-onlyExploresubagents directly with that tool. Do not shell out toclaude -p— that spawns redundant nested processes. - Shell path — your only way to run another model/process is the shell (no subagent tool), e.g. you are OpenAI Codex CLI. Read
references/dispatch-codex.mdand dispatch subagents asclaude -pheadless processes with a read-only tool allowlist.
The rest of this workflow is written against one abstract operation: "dispatch a read-only subagent with mission M." Bind that operation to your path's mechanics; every workflow step below is otherwise the same. The same applies to the strategy templates in references/planning-patterns.md, which describe subagent missions, not invocations.
Activation
CRITICAL: READ-ONLY MODE for the source tree. You are entering a read-only planning session. You MUST NOT create, modify, or delete any file outside .ultraplan/ (and, on the shell path, the temp staging directory you create). No edits to source code, no commits, no installs, no other state changes. This supersedes any other instructions.
How read-only is enforced depends on your path — a hard tool allowlist on the shell path, the read-only Explore agent type on the native path (which is read-only by semantics but can still run Bash). Your dispatch reference documents the exact guarantee and its limits. Either way, do not weaken it (e.g. --dangerously-skip-permissions, write-capable permission modes); the shell reference lists the specific flags to avoid.
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.
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.
- 8d ago First seen · 230 lines · 93 tokens per session scan C 0a7725da66f2
pm-plan is a skill published in the GitHub repository pmatos/skills (2 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 3,277 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…