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/asachs01/float-mcp/add-subtaskgit clone --depth 1 https://github.com/asachs01/float-mcpWhat 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 | $0.00000 | $0.00457 |
| Opus 5 | $0.00000 | $0.00229 |
| Sonnet 5 | $0.00000 | $0.00091 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
add-subtask 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 2d 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.
This is a copy
100% identical to add-subtask — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Add a subtask to a parent task.
Arguments: $ARGUMENTS
Parse arguments to create a new subtask or convert existing task.
Adding Subtasks
Creates subtasks to break down complex parent tasks into manageable pieces.
Argument Parsing
Flexible natural language:
- "add subtask to 5: implement login form"
- "break down 5 with: setup, implement, test"
- "subtask for 5: handle edge cases"
- "5: validate user input" → adds subtask to task 5
Execution Modes
1. Create New Subtask
task-master add-subtask --parent=<id> --title="<title>" --description="<desc>"
2. Convert Existing Task
task-master add-subtask --parent=<id> --task-id=<existing-id>
Smart Features
-
Automatic Subtask Generation
- If title contains "and" or commas, create multiple
- Suggest common subtask patterns
- Inherit parent's context
-
Intelligent Defaults
- Priority based on parent
- Appropriate time estimates
- Logical dependencies between subtasks
-
Validation
- Check parent task complexity
- Warn if too many subtasks
- Ensure subtask makes sense
Creation Process
- Parse parent task context
- Generate subtask with ID like "5.1"
- Set appropriate defaults
- Link to parent task
- Update parent's time estimate
Example Flows
/project:tm/add-subtask to 5: implement user authentication
→ Created subtask #5.1: "implement user authentication"
→ Parent task #5 now has 1 subtask
→ Suggested next subtasks: tests, documentation
/project:tm/add-subtask 5: setup, implement, test
→ Created 3 subtasks:
#5.1: setup
#5.2: implement
#5.3: test
Post-Creation
- Show updated task hierarchy
- Suggest logical next subtasks
- Update complexity estimates
- Recommend subtask order
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.
- 2d ago First seen · 82 lines · 0 tokens per session scan A 4370e371f9b7
add-subtask is a command published in the GitHub repository asachs01/float-mcp (2 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 457 tokens. A static security scan graded it A with 0 findings. It is 100% identical to add-subtask, differing in 8 lines, and is treated as a copy.
Other commands, from other repositories
pm-init
Initialize local .pm governance; detect Spec Kit; if absent, analyze the repo and draft a PRD for user confirmation; after confirm/skip run a technical light scan.
pm-all
Full technical governance scan; rebuild .pm/dashboard. Default does not wait on draft PRD. Use --compare-baseline only after a confirmed PRD/charter.
pm-done
Close a todo (TODO-xxx), sync completed.md, refresh overview.
pm-export
Export desensitized governance summary markdown for sharing or machine switch.
pm-next
Claim the single next governance todo (marks inprogress).
pm-outline
Generate detailed project outline and draft charter from user intent (empty/new projects).