verify-plan

A command that starts a task-plan-verifier agent to review Tasker task definitions against a specification, capability map, and user preferences. It reports whether the plan is ready, ready with notes, or blocked.

In plain words
What is it for?
Use it after editing task files or after fixing reported problems. It checks the files in the Tasker planning directories and can include the user's coding preferences when available.
Why use it?
It catches task definitions that do not match the project requirements before implementation begins. This gives the team a clear decision about whether planning can proceed.

Command

Install

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.

agentmods
npx agentmods add commands/dowwie/tasker/verify-plan
Clone the repo
git clone --depth 1 https://github.com/Dowwie/tasker
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 182 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00182
Opus 5 $0.00000 $0.00091
Sonnet 5 $0.00000 $0.00036
Haiku 4.5 $0.00000 $0.00018

Measured 2d ago against content hash 5248042e4a32, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

verify-plan 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.

internal/commands/verify-plan.md · 31 lines

What it actually says

Verify Plan

Spawn the task-plan-verifier subagent to evaluate task definitions.

Instruction

Spawn the task-plan-verifier agent with:

Verify task definitions for planning

Spec: .tasker/inputs/spec.md
Capability Map: .tasker/artifacts/capability-map.json
Tasks Directory: .tasker/tasks/
User Preferences: ~/.claude/CLAUDE.md (if exists)

When to Use

  • After editing task files to check alignment
  • To re-run validation after fixing BLOCKED issues
  • To verify tasks match your ~/.claude/CLAUDE.md coding preferences

Verdicts

Verdict Meaning
READY All tasks pass, can proceed
READY_WITH_NOTES Pass with minor issues documented
BLOCKED Critical issues must be fixed first
Changes

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.

  1. 2d ago First seen · 31 lines · 0 tokens per session scan A 5248042e4a32

Subscribe to this mod's changes

verify-plan is a command published in the GitHub repository Dowwie/tasker (19 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 182 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 2026-08-30.