Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/joshuaboys/gxnpx agentmods add skills/joshuaboys/gx/aps-planningWrote 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/joshuaboys/gx/aps-planning)<a href="https://agentmods.dev/skills/joshuaboys/gx/aps-planning"><img src="https://agentmods.dev/badge/skills/joshuaboys/gx/aps-planning/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/joshuaboys/gx/aps-planning"><img src="https://agentmods.dev/badge/skills/joshuaboys/gx/aps-planning.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.01758 |
| Opus 5 | $0.00000 | $0.00879 |
| Sonnet 5 | $0.00000 | $0.00352 |
| Haiku 4.5 | $0.00000 | $0.00176 |
Grade A, and why
aps-planning 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 10d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
APS Planning Skill
Persistent, structured planning for AI agents using Anvil Plan Spec.
What This Skill Does
This skill teaches you to use APS (Anvil Plan Spec) — a markdown-based
planning format — as persistent memory for complex tasks. APS files live in
plans/ and survive context resets, session clears, and handoffs.
Core insight: Your context window is RAM (volatile, limited). The filesystem is disk (persistent, unlimited). Anything important gets written to APS files.
Hard Rules
-
Plan before building. Never start a complex task without an APS file. If
plans/doesn't exist, create it. If no spec covers this work, create one before writing code. -
Read before deciding. Before any major implementation decision, re-read the relevant APS spec. After many tool calls, your original goals drift out of your attention window. Re-reading brings them back.
-
Update as you go. After completing a work item or discovering something important, update the APS file immediately. Stale specs lose trust.
-
Never skip validation. Every work item has a Validation field. Run it before marking anything complete.
-
Specs describe intent, not implementation. Write what and why, never how. Implementation emerges from code patterns and agent judgment.
When to Trigger APS Planning
Use APS when the user asks you to:
- Build a new feature with multiple parts
- Plan, design, or architect something
- Work on something that spans multiple files or domains
- Execute work that needs coordination or sequencing
- Pick up where a previous session left off
Don't use APS for: Quick one-off fixes, single-file edits, questions, or trivial changes.
The APS Workflow
Assess → Plan → Execute → Validate → Update
1. Assess
Before planning, understand what exists:
1. Check: Does plans/ directory exist?
2. Check: Does plans/index.aps.md exist?
3. Check: Are there module files in plans/modules/?
4. Read plans/aps-rules.md if present (agent guidance)
5. Identify: Is this new work or continuing existing work?
What ships with it
15 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.
- examples.md 4.5 KB
- hooks.md 6.1 KB
- reference.md 3.4 KB
- scripts/check-complete.ps1 3.7 KB runs code
- scripts/check-complete.sh 2.9 KB runs code
- scripts/enforce-plan-update.ps1 4.1 KB runs code
- scripts/enforce-plan-update.sh 3.4 KB runs code
- scripts/init-session.ps1 4.5 KB runs code
- scripts/init-session.sh 3.5 KB runs code
- scripts/install-hooks.ps1 8.8 KB runs code
- scripts/install-hooks.sh 6.4 KB runs code
- scripts/post-tool-nudge.ps1 430 B runs code
- scripts/post-tool-nudge.sh 448 B runs code
- scripts/pre-tool-check.ps1 557 B runs code
- scripts/pre-tool-check.sh 515 B runs code
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.
- 10d ago First seen · 263 lines · 0 tokens per session scan A 2e743f34f750
aps-planning is a skill published in the GitHub repository joshuaboys/gx (10 stars, last pushed 28d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,758 tokens. 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.