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 Sh3rd3n/megazord --skill plangit clone --depth 1 https://github.com/Sh3rd3n/megazordWrote 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/sh3rd3n/megazord/plan)<a href="https://agentmods.dev/skills/sh3rd3n/megazord/plan"><img src="https://agentmods.dev/badge/skills/sh3rd3n/megazord/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 | $0.00012 | $0.04852 |
| Opus 5 | $0.00006 | $0.02426 |
| Sonnet 5 | $0.00002 | $0.00970 |
| Haiku 4.5 | $0.00001 | $0.00485 |
Grade A, and why
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 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.
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 — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mz:plan
Plan a phase by orchestrating research and planning agents. Produces PLAN.md files with task breakdown, dependencies, and completion criteria.
Reference @skills/init/design-system.md for visual output formatting.
Reference @skills/shared/presentation-standards.md for content formatting rules.
Reference @skills/shared/terminology.md for official term definitions.
Reference @skills/plan/agents.md for agent definitions and spawning patterns.
Step 1: Display Banner
Output the stage banner:
╔═══════════════════════════════════════════════╗
║ ⚡ MEGAZORD ► PLANNING ║
╚═══════════════════════════════════════════════╝
Step 2: Load Project Context
Read .planning/megazord.config.json. If missing, display an error box and stop:
╔═══════════════════════════════════════════════╗
║ ✗ Project Not Initialized ║
╠═══════════════════════════════════════════════╣
║ No megazord.config.json found. ║
║ Run /mz:init to set up your project first. ║
╚═══════════════════════════════════════════════╝
If config exists, continue loading:
- Read
.planning/STATE.mdfor current position. - Read
.planning/ROADMAP.mdfor phase listing. - Parse the user's message for arguments:
- A phase number (e.g.,
/mz:plan 3or/mz:plan phase 3) - The
--skip-researchflag - Phase management subcommands:
add-phase,remove-phase,insert-phase(see Step 2b)
- A phase number (e.g.,
Store all loaded content in memory -- it will be embedded in Task prompts later.
Brownfield Codebase Map Detection
After loading config, check for codebase map integration:
- Check if
.planning/codebase/SUMMARY.mdexists. - If it exists: Read the summary content and store it in memory for later embedding in the planner prompt (Step 6).
> Codebase Map ✓ Loaded codebase summary (.planning/codebase/SUMMARY.md) - If it does NOT exist but existing code is detected (check for the presence of any of these in the project root:
package.json,src/,lib/,app/,Cargo.toml,go.mod,requirements.txt,pyproject.toml, orpom.xml): Display a soft warning:
Use AskUserQuestion (header: "Brownfield", 10 chars):> Brownfield ! Existing code detected but no codebase map found. Run /mz:map first for better roadmap quality, or continue without.- "Continue without map"
- "Run /mz:map first" (display "Run
/mz:mapto analyze the codebase, then re-run/mz:plan." and exit)
- If no codebase map and no existing code detected: Skip silently (greenfield project, no map needed).
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.
- 6d ago First seen · 494 lines · 12 tokens per session scan A 90eba4d4b733
plan is a skill published in the GitHub repository Sh3rd3n/megazord (3 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 4,852 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
finding-duplicate-functions
Use when auditing a codebase for semantic duplication — functions that do the same thing but have different names or implementations, especially common in LLM-generated codebases.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
llm-friendly-context
Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.
sync-check
Walks the documentation dependency web after a CLI code change and reports which downstream files (skills, SOPs, READMEs, plugin references) are out of sync. Use after fixing a bug, adding a command, changing auth behavior, refactoring, or before committing — and when the user says "sync check", "update docs"…
alive-people
Weekly -- cross-reference people mentions, nudge stale contacts.