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.
git clone --depth 1 https://github.com/varienos/agentic-workflowWrote 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/varienos/agentic-workflow/task-plan-review.skeleton)<a href="https://agentmods.dev/commands/varienos/agentic-workflow/task-plan-review.skeleton"><img src="https://agentmods.dev/badge/commands/varienos/agentic-workflow/task-plan-review.skeleton/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/commands/varienos/agentic-workflow/task-plan-review.skeleton"><img src="https://agentmods.dev/badge/commands/varienos/agentic-workflow/task-plan-review.skeleton.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 | $0.00000 | $0.04299 |
| Opus 5.5 | $0.00000 | $0.01720 |
| Sonnet 5.5 | $0.00000 | $0.00860 |
| Haiku 4.5 | $0.00000 | $0.00430 |
Grade C, and why
task-plan-review.skeleton scanned grade C with 1 finding 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 21d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
> **Rule:** Do not refuse a second pass because an earlier review exists. How it starts
The opening of the file, as written. The whole thing — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Plan Review — 3+1 Agent Plan Inspection
Inspect backlog tasks that are not implemented yet. Check the plan against the current codebase and apply the needed corrections on the task. Usage:
/task-plan-review <task-id>,/task-plan-review task-123 task-456,/task-plan-review --status "To Do"Divider: This reviews an unimplemented plan. For delivered code, use/task-review.
Purpose: Review plans created by /task-plan before /task-hunter implements them. Do not write product code. Correct plan quality, file references, acceptance checks, and scope.
A blind review is forbidden. Do not spawn agents, edit the plan, or raise the review count until the validity gate in section 1.4 passes.
Several reviews of the same plan are allowed. The goal is the best plan, not a single pass. Earlier ## Plan Review notes are audit history. They are not a reason to skip this pass. Each finished pass writes a [N] counter at the start of the title (Step 4.4).
No model pin. The active host chooses the model. Subagents inherit it. Claude is one host, not the product.
Code relationship: search, read, and the shell. Do not assume a product layout. Use the paths in the manifest and in ../Codebase/.
Step 1 — Load the task
1.1 — Resolve the argument
| Input | Behavior |
|---|---|
task-123 / TASK-123 / 123 |
One task |
| Several ids | Review them in order. Independent tasks may be loaded together |
--status "To Do" |
backlog task list -s "To Do". Show the list. Continue after confirmation, or with --all |
| Empty | List the latest 5 To Do tasks and ask which ones to review |
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.
- 21d ago First seen · 377 lines · 0 tokens per session scan C 2c9a784b8028
task-plan-review.skeleton is a command published in the GitHub repository varienos/agentic-workflow (59 stars, last pushed 22d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,299 tokens. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-25.
Other commands, from other repositories
portfolio
Show a read-only hub-wide portfolio of canonical Ideas and active Projects without duplicating topic-owned records.
repo-architect
Repository structure optimization and multi-repo management with ruv-swarm coordination for scalable project architecture and development workflows.
issue-tracker
Intelligent issue management and project coordination with ruv-swarm integration for automated tracking, progress monitoring, and team coordination.
paul:add-phase
Add a new phase to current milestone.
issue-triage
Intelligent issue classification and triage.
project
Manage projects inside a topic wiki. Projects are folders under output/projects/ that group related outputs (playbooks, images, code, data) with a goal captured in WHY.md.