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/bookedsolidtech/helixir/plan-workgit clone --depth 1 https://github.com/bookedsolidtech/helixirWhat 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 | $0.00183 |
| Opus 5 | $0.00000 | $0.00092 |
| Sonnet 5 | $0.00000 | $0.00037 |
| Haiku 4.5 | $0.00000 | $0.00018 |
Grade A, and why
plan-work 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
Invoke the product-owner agent to plan and propose tasks for a goal.
Instructions
- First, read
.rea/tasks.jsonlto understand the current backlog - Ask the user what they want to accomplish (if not already provided as an argument)
- Spawn the
product-owneragent to:- Review existing tasks to avoid duplication
- Propose a set of new tasks for the goal
- Show the proposed tasks in a table format
- Wait for user confirmation before creating any tasks
- Only create tasks the user explicitly approves
Important
- NEVER auto-create tasks without user approval
- Show proposed tasks as a preview table first
- Respect the product-owner agent's guardrails (max 10 tasks, no critical urgency without approval, parent grouping for 5+)
- If the goal is vague, ask clarifying questions before proposing tasks
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 · 20 lines · 0 tokens per session scan A 3d436ab25b09
plan-work is a command published in the GitHub repository bookedsolidtech/helixir (5 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 183 tokens. 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 commands, from other repositories
interactive-planning
File-based planning with interactive gates + native task tracking. Supports task-based (single plan file) and spec-driven (multi-file specs with manifest) modes. Phase/Sprint/Spec hierarchy with dependency DAG.
ijfw-audit
Run the IJFW audit gate for the current workflow phase. Usage: /ijfw-audit [phase name].
pm-review
Review local git diff with reasoning + snippets; cross-check; dispose findings into the rules library.
test-integration
Write integration tests for component boundaries.
learn
Learn about Task Master capabilities through interactive exploration.
to-pending
Command "to-pending" from WYRE-AI/autotask-mcp, covering setting task to pending, execution, validation and smart actions.