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/engagegit 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/engage)<a href="https://agentmods.dev/commands/madappgang/magus/engage"><img src="https://agentmods.dev/badge/commands/madappgang/magus/engage.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 | $0.00027 | $0.00804 |
| Opus 5 | $0.00014 | $0.00402 |
| Sonnet 5 | $0.00005 | $0.00161 |
| Haiku 4.5 | $0.00003 | $0.00080 |
Grade A, and why
engage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GTD Engage — Set Active Task
You are implementing the GTD engage command. The user wants to focus on a specific GTD task, loading its subtasks into the current session.
Parse the Input
The user invoked /gtd:engage with a task identifier. Extract:
- identifier: Task ID (e.g.,
gtd-a1b2c3) or partial task subject text to search
Find the Task
Run this Bash command to find and set the active task:
CWD=$(pwd)
GTD_FILE="${CWD}/.claude/gtd/tasks.json"
GTD_LIB="${CLAUDE_PLUGIN_ROOT}/hooks/gtd-lib.sh"
IDENTIFIER="<user input>"
# Check if GTD store exists
if [ ! -f "$GTD_FILE" ]; then
echo "No GTD store found. Run /gtd:capture to create one."
exit 0
fi
# Search by ID or subject (case-insensitive partial match)
TASK=$(jq --arg id "$IDENTIFIER" --arg search "$IDENTIFIER" '
.tasks[] | select(
.completed == null and
(.id == $id or (.subject | ascii_downcase | contains($search | ascii_downcase)))
)
' "$GTD_FILE" | head -1)
if [ -z "$TASK" ]; then
echo "Task not found: \"$IDENTIFIER\". Run /gtd:next to see available tasks."
exit 0
fi
TASK_ID=$(echo "$TASK" | jq -r '.id')
TASK_SUBJECT=$(echo "$TASK" | jq -r '.subject')
# Set as active task
TMP="${GTD_FILE}.tmp.$$"
jq --arg id "$TASK_ID" '.activeTaskId = $id' "$GTD_FILE" > "$TMP" && mv "$TMP" "$GTD_FILE"
# Count subtasks (parentId == task_id)
SUBTASK_COUNT=$(jq --arg id "$TASK_ID" '[.tasks[] | select(.parentId == $id and .completed == null)] | length' "$GTD_FILE")
# Display confirmation with subtask tree
bun run "${CLAUDE_PLUGIN_ROOT}/tools/gtd-display.ts" engage "$TASK_ID"
After Setting Active Task
- Tell the user which task is now active and how many subtasks it has.
- Load any existing subtasks (tasks where parentId == the active task ID) into the session TaskList via TaskCreate with metadata
{ gtdId: "<subtask_id>", gtdParent: "<active_id>" }. - Show the active task's details: subject, context, energy, timeEstimate if set.
- If the dev plugin is installed (check if
/dev:devis available): suggest "Ready to implement? Run/dev:devto start development." - Offer: "Run
/gtd:nextto see all next actions, or/gtd:statusfor the full dashboard."
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 · 80 lines · 27 tokens per session scan A dd9e4a02fcb0
engage is a command published in the GitHub repository MadAppGang/magus (9 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 804 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 2026-09-04.
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.