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 23blocks-OS/ai-maestro-plugins --skill planninggit clone --depth 1 https://github.com/23blocks-OS/ai-maestro-pluginsWrote 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/23blocks-os/ai-maestro-plugins/planning)<a href="https://agentmods.dev/skills/23blocks-os/ai-maestro-plugins/planning"><img src="https://agentmods.dev/badge/skills/23blocks-os/ai-maestro-plugins/planning.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 | $0.00058 | $0.01958 |
| Opus 5 | $0.00029 | $0.00979 |
| Sonnet 5 | $0.00012 | $0.00392 |
| Haiku 4.5 | $0.00006 | $0.00196 |
Grade B, and why
planning scanned grade B 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 6d 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls ~/.claude/skills/planning/templates/ How it starts
The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Maestro Planning Skill
The Problem This Solves: EXECUTION
This skill solves the execution problem - losing focus during complex tasks:
| Problem | Symptom | This Skill Fixes It |
|---|---|---|
| Goal drift | Forgot original objective after 50 tool calls | Re-read plan before decisions |
| Lost progress | Can't remember what phase I'm in | Phase tracking in task_plan.md |
| Repeated errors | Make same mistake twice | Error log prevents repetition |
| Session loss | Can't resume after /clear | Planning files persist on disk |
Note: This is different from the Memory skill (which solves recall of past conversations). Planning solves staying focused NOW.
Core Principle
Context Window = RAM (volatile, limited, fast)
Filesystem = Disk (persistent, unlimited, explicit read required)
Anything important gets written to disk.
Output Directory
Planning output files (task_plan.md, findings.md, progress.md) should be written to:
- The directory specified by the
AIMAESTRO_PLANNING_DIRenvironment variable (if set) - Otherwise,
docs_dev/in the current project root - Create the directory if it does not exist
Do NOT write planning files to the project root — use docs_dev/ to avoid cluttering the project.
The 3-File Pattern
Create these files in docs_dev/ (not the project root or the skill directory):
| File | Purpose | Update When |
|---|---|---|
task_plan.md |
Goals, phases, decisions, errors | After each phase |
findings.md |
Research, discoveries, resources | During research |
progress.md |
Session log, test results | Throughout session |
Quick Start
Before any complex task (3+ steps):
# 1. Determine output directory
PLAN_DIR="${AIMAESTRO_PLANNING_DIR:-docs_dev}"
mkdir -p "$PLAN_DIR"
# 2. Create planning files from templates
cat ~/.claude/skills/planning/templates/task_plan.md > "$PLAN_DIR/task_plan.md"
cat ~/.claude/skills/planning/templates/findings.md > "$PLAN_DIR/findings.md"
cat ~/.claude/skills/planning/templates/progress.md > "$PLAN_DIR/progress.md"
# 3. Edit task_plan.md with your specific goal and phases
What ships with it
3 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.
- 6d ago First seen · 307 lines · 58 tokens per session scan B fead3717b5de
planning is a skill published in the GitHub repository 23blocks-OS/ai-maestro-plugins (9 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 1,958 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
coding-investigation
Investigate unfamiliar code behavior, or answer an exact symbol's definition, callers, callees, references, impact, and cross-repository relationship questions. Use it to trace activation, ownership, data flow, configuration, registration, and runtime wiring with bounded source evidence without mutating code; do not…
skill-installer
Create, import, update, validate, or relocate portable Agent Skill bundles with SKILL.md, on-demand references, deterministic scripts, output assets, UI metadata, and EvoFlux mode settings. Use for explicit skill authoring or installation; do not use for invoking an existing skill, changing agent configuration, or…
Read, create and manipulate PDF files — extract text and tables, merge, split, rotate, reorder and delete pages, read and fill AcroForm fields, add or strip metadata, encrypt and decrypt, and generate new PDFs from HTML or from scratch. Also covers rasterising pages to images so a PDF can actually be looked at, and…
easd-implement
Implement bounded work for an active EASD run under its accepted specification and AC ownership. Use only when EASD has authorized implementation; do not use while the run is Intent, authoring, draft, or merely accepted.
easd-verify
Run the final EASD integration and evidence gate against accepted AC policies, then prepare a convergence recommendation. Use after implementation and any required independent review; not for task-local code review or ordinary tests outside EASD.
coding-debugging
Use this skill when a test, build, runtime path, integration, or concurrent workflow fails and the responsible condition is unknown. It is for reproducing symptoms, isolating a cause, fixing it when authorized, and proving the regression; do not use it for general code exploration, proactive review, or an…