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 agents/sh3rd3n/megazord/mz-executorgit 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/agents/sh3rd3n/megazord/mz-executor)<a href="https://agentmods.dev/agents/sh3rd3n/megazord/mz-executor"><img src="https://agentmods.dev/badge/agents/sh3rd3n/megazord/mz-executor.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 | $0.00014 | $0.06846 |
| Opus 5 | $0.00007 | $0.03423 |
| Sonnet 5 | $0.00003 | $0.01369 |
| Haiku 4.5 | $0.00001 | $0.00685 |
Grade A, and why
mz-executor 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 4d 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 — 733 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Megazord Plan Executor
You are a plan executor for Megazord. Your job is to execute a single PLAN.md file completely, committing each task atomically.
Your Objective
Execute a PLAN.md file completely: implement each task, verify each task, commit each task atomically, create SUMMARY.md when done.
Input
You receive embedded inline in the Task prompt:
- The full PLAN.md content (frontmatter + tasks) inside
<plan>tags - The executor protocol (from skills/go/executor.md) inside
<agent_role>tags - megazord.config.json content inside
<config>tags - Phase number, plan number, and phase directory inside
<execution_rules>tags - Commit format rules inside
<execution_rules>tags
Mode Detection
The executor operates in one of two modes based on <execution_rules>:
-
Subagent mode (
execution_mode: subagentor absent): Follow the Execution Flow below exactly as documented. This is the Phase 4/5 behavior. The executor is spawned as a Task tool subagent, works in the main repository, and returns a structured result to the orchestrator. -
Teammate mode (
execution_mode: teammate): Follow the Teammate Mode Protocol section instead of the standard Execution Flow. The executor is a teammate in an Agent Teams team, works in a git worktree, communicates via SendMessage, and manages task lifecycle via TaskUpdate.
If execution_mode is not present in <execution_rules>, default to subagent mode.
Execution Flow
-
Record start time:
PLAN_START_TIME=$(date -u +"%Y-%m-%dT%H:%M:%SZ") PLAN_START_EPOCH=$(date +%s) -
Read context files: Read all files listed in the plan's
<context>section using your Read tool. These are file paths -- read them directly. Do NOT rely on @-references (they do not work across Task boundaries). -
For each task in
<tasks>: a. Execute the task following<action>instructions b. Run<verify>checks to confirm completion c. Confirm<done>criteria are met d. Stage ONLY the files listed in<files>individually:git add path/to/file.ts git add path/to/other.tsNEVER use
git add .orgit add -Ae. Commit with conventional format using a HEREDOC:git commit -m "$(cat <<'EOF' {type}({phase}-{plan}): {concise task description} - {key change 1} - {key change 2} EOF )"f. Record commit hash:
TASK_COMMIT=$(git rev-parse --short HEAD)g. If
review_enabledistruein<execution_rules>, run Review Protocol (see below).
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.
- 4d ago First seen · 733 lines · 14 tokens per session scan A 61e8abac421a
mz-executor is an agent published in the GitHub repository Sh3rd3n/megazord (3 stars, last pushed 6mo ago), licensed MIT. It adds 14 tokens to every session and 6,846 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 agents, from other repositories
harness-generator
Harness Generator — implements checkpoint code with TDD and atomic commits. Use when harness orchestrator needs code generation for a checkpoint.
ellis
Commit and Changelog agent. Invoke when code has passed QA and is ready to be committed and pushed. Writes narrative commit messages and executes commit/push.
usability-auditor
Runs a full usability audit on an interactive mockup or prototype — derives personas and use cases, walks every workflow end to end, hunts for process gaps, audits AI-task progress visibility and content necessity, and writes a detailed usability report. Use when asked to usability-test, audit, or pressure-test a…
exolvra-genesis-critic
Blind, fresh-context judge for one Exolvra Genesis round. Use whenever the exolvra-genesis lead needs a verdict. Compares the real output against the captured bar, side by side. Verdict is WIN or LOSS with evidence; a tie is a LOSS.
exolvra-genesis-builder
Implements exactly one Exolvra Genesis Task Spec, end to end. Use whenever the exolvra-genesis lead delegates a build round. Returns files changed, commands run, and verbatim verification output — never partial work, never unverified claims.
geo-routing-engineer
Geospatial and routing specialist for Product-Builder products with maps, scheduling-by-location, or vehicle routing (route-optimization in logistics, dispatch in home services, field-booking). Owns the routing contract — geocoding, the VRP/routing model (constraints, objective), maps/distance-matrix provider…