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/smekai/taskplanner/next-taskgit clone --depth 1 https://github.com/smekai/taskplannerWhat 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 | $0.00013 | $0.00339 |
| Opus 5 | $0.00006 | $0.00169 |
| Sonnet 5 | $0.00003 | $0.00068 |
| Haiku 4.5 | $0.00001 | $0.00034 |
Grade A, and why
next-task 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.
What it actually says
Next Task
Pick the highest-priority unstarted task and begin implementation.
Steps
Determine the absolute current repository root first and pass it as workspace_root on every MCP call.
- Call
taskplanner_listwithstate: "Next"to find tasks queued for implementation. - If no tasks are in Next, fall back to
taskplanner_listwithstate: "Backlog". - Select the first task (highest priority, since tasks are sorted by priority).
- Show the user which task you are picking and ask for confirmation before proceeding.
- Once confirmed:
a. Call
taskplanner_moveto move the task to "In Progress". b. Read.tasks/config.jsonto check ifaiPlanRequiredis true. c. If plan is required, write a### Plansubsection under the task heading inIN_PROGRESS.mdbefore writing any code. The plan should have 3-7 bullets covering: intended changes, key files, and notable risks. d. Implement the task. e. When done, calltaskplanner_moveto move the task to "Done". f. Add a CHANGELOG.md entry under## [Unreleased]in the appropriate subsection (Added, Changed, Fixed, Removed).
Conventions
- Do NOT change task IDs.
- Keep the
---separator between tasks in markdown files. - When moving to Done, condense the
### Planto a short summary of what was actually done.
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 · 31 lines · 13 tokens per session scan A edb67805abde
next-task is a command published in the GitHub repository smekai/taskplanner (19 stars, last pushed 4d ago), licensed MIT. It adds 13 tokens to every session and 339 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 2026-08-30.
Other commands, from other repositories
advisor
Advisory gate for triage or plan decisions. Spawns a second-opinion agent that challenges assumptions, surfaces risks, and proposes alternatives before the decision commits. Based on Anthropic advisor tool pattern.
guide
You are a triage agent who continuously prioritizes loom:issue issues by applying loom:urgent to the top 3 priorities.
pm-review
Review local git diff with reasoning + snippets; cross-check; dispose findings into the rules library.
new
Creates a new item in a module that supports the new capability.
card
Open one self-contained OverClick card.
linear-bulk
Apply the same change to many Linear issues at once. Dry-run by default.