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 discussgit 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/discuss)<a href="https://agentmods.dev/skills/sh3rd3n/megazord/discuss"><img src="https://agentmods.dev/badge/skills/sh3rd3n/megazord/discuss/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/sh3rd3n/megazord/discuss"><img src="https://agentmods.dev/badge/skills/sh3rd3n/megazord/discuss.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 | $0.00011 | $0.02336 |
| Opus 5 | $0.00005 | $0.01168 |
| Sonnet 5 | $0.00002 | $0.00467 |
| Haiku 4.5 | $0.00001 | $0.00234 |
Grade A, and why
discuss 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 8d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mz:discuss
Facilitate Socratic brainstorming that explores 5+ alternative approaches before converging on a direction. Produces CONTEXT.md-compatible output for downstream planning. Works both within phase context and as standalone brainstorming.
Reference @skills/init/design-system.md for visual output formatting.
Reference @skills/shared/presentation-standards.md for content formatting and Next Up block rules.
Reference @skills/shared/interview-language.md for language detection and session-wide persistence rules.
Reference @skills/shared/terminology.md for official term definitions.
Step 1: Display Banner
Output the stage banner:
+===============================================+
| MEGAZORD > DISCUSS |
+===============================================+
Step 1b: Language Detection
Detect the user's language from their first natural-language message following the rules in @skills/shared/interview-language.md.
Apply the detected language to all Socratic dialogue: seed questions, challenges, suggestions, summaries, convergence prompts, and the final output document's prose sections.
Keep in English: file paths, CONTEXT.md section headers (<domain>, <decisions>, <specifics>, <deferred>), technical terms, and command names.
Step 2: Determine Context
Parse the user's invocation to determine where output will be written.
Phase context detection (in priority order):
-
Explicit phase number -- user provides a phase number (e.g.,
/mz:discuss 7):- Read
.planning/STATE.mdto resolve the phase directory - Target:
{phase_dir}/{padded}-CONTEXT.md(e.g.,.planning/phases/07-quality-and-debugging-skills/07-CONTEXT.md)
- Read
-
Active phase -- no explicit number, but a phase is in progress:
- Read
.planning/STATE.mdfor current position - If a phase is active (status is "In Progress"): target that phase's CONTEXT.md
- If the phase CONTEXT.md already exists, note it will be overwritten
- Read
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.
- 8d ago First seen · 248 lines · 11 tokens per session scan A a09c3fe5e825
discuss is a skill published in the GitHub repository Sh3rd3n/megazord (3 stars, last pushed 6mo ago), licensed MIT. It adds 11 tokens to every session and 2,336 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.