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/markmhendrickson/foundation/create-plannpx skills add markmhendrickson/foundation --skill create-plangit clone --depth 1 https://github.com/markmhendrickson/foundationWhat 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 | $0.00025 | $0.00686 |
| Opus 5 | $0.00013 | $0.00343 |
| Sonnet 5 | $0.00005 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00069 |
Grade A, and why
create-plan 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 yesterday.
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.
This is a copy
95% identical to create-plan — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create New Plan
Create a new plan entity in Neotoma with title = {{input:title}}.
Follow the complete workflow in foundation/development/plan_workflow.md. Configuration is read from foundation-config.yaml.
This workflow can also be triggered automatically via .cursor/rules/plan_detection.mdc when you mention planning-related patterns in natural language (e.g., "create plan", "new plan"). Both paths execute the same workflow.
Workflow Overview
Implements Checkpoint 0 of the plan creation workflow:
- Collect required plan fields from the user
- Run alignment check (summary → user confirms)
- Store plan as a Neotoma
planentity - Create relationships to related entities
- Optionally rebuild the
neotoma-plansmirror
Tasks
-
Collect required fields:
Ask the user for any missing required fields:
title— Short, imperative namedescription— Problem being solved and why it mattersscope— What is explicitly in scopeout_of_scope— What is explicitly out of scopesuccess_criteria— Measurable conditions for completionstatus— Default todraft
Optional fields to offer (collect if relevant):
priority(P0/P1/P2/P3)phasetarget_releasedeliverablesdependencies(canonical names of plans this plan requires)testing_notesobservability_notes
-
Alignment check:
After collecting fields, produce a concise summary:
- Problem it solves and why it exists
- What is explicitly in scope and out of scope
- Critical constraints or invariants
Ask: "Does this accurately capture what you want this plan to do?"
Incorporate corrections and re-summarize if changes are substantial. Do not proceed until the user confirms.
-
Store the plan:
Use
storeorsubmit_entitywith:entity_type: plan- All collected fields as snapshot fields
-
Create relationships (if relevant entities are mentioned or known):
REFERS_TOfor objectives, releases, or parent plansDEPENDS_ONfor plans this plan requiresINFORMED_BYfor issues, feedback, or research
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.
- yesterday First seen · 93 lines · 25 tokens per session scan A 78ed4c74bcf4
create-plan is a skill published in the GitHub repository markmhendrickson/foundation (2 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 686 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to create-plan, differing in 9 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
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…
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…
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…