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 commands/madappgang/magus/nextgit clone --depth 1 https://github.com/MadAppGang/magusWrote 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/commands/madappgang/magus/next)<a href="https://agentmods.dev/commands/madappgang/magus/next"><img src="https://agentmods.dev/badge/commands/madappgang/magus/next.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 | $0.00048 | $0.00477 |
| Opus 5 | $0.00024 | $0.00238 |
| Sonnet 5 | $0.00010 | $0.00095 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
next scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
GTD Next Actions
You are implementing the GTD next command. The user wants to see their actionable next actions, optionally filtered.
Parse the Input
Extract optional filters from the command arguments:
--context @tag— filter by context tag (e.g.,@code,@review)--energy high|medium|low— filter by energy level--time <minutes>— show only tasks taking <= N minutes--project <name>— filter by project name--waiting— show Waiting For list instead of Next Actions
Display Tasks
Run this Bash command (set filter variables based on parsed arguments):
# Set filter variables from parsed input (replace with actual values or leave empty)
CONTEXT_FILTER="" # e.g. "@code" or ""
ENERGY_FILTER="" # e.g. "high" or ""
TIME_FILTER="" # e.g. "60" or ""
SHOW_WAITING=false # true if --waiting flag
# Build display command
DISPLAY_ARGS="next"
[ -n "$CONTEXT_FILTER" ] && DISPLAY_ARGS="$DISPLAY_ARGS --context $CONTEXT_FILTER"
[ -n "$ENERGY_FILTER" ] && DISPLAY_ARGS="$DISPLAY_ARGS --energy $ENERGY_FILTER"
[ -n "$TIME_FILTER" ] && DISPLAY_ARGS="$DISPLAY_ARGS --time $TIME_FILTER"
[ "$SHOW_WAITING" = "true" ] && DISPLAY_ARGS="$DISPLAY_ARGS --waiting"
bun run "${CLAUDE_PLUGIN_ROOT}/tools/gtd-display.ts" $DISPLAY_ARGS
After Showing Tasks
- If tasks were shown: offer "Run
/gtd:engage <id>to set an active task, or/gtd:clarifyto clarify inbox items." - If
--waitingwas used: mention checking for follow-ups on items waiting > 7 days. - If no filters applied and > 10 tasks: suggest using
--context @codeor--energy highto narrow down.
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.
- yesterday First seen · 45 lines · 48 tokens per session scan A cbae98e970c1
next is a command published in the GitHub repository MadAppGang/magus (9 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 477 once invoked, about $0.0002 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 2026-09-04.
Other commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
release
Perform a full release: generate release notes, bump version, commit, tag, and push.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.