Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/varienos/agentic-workflownpx agentmods add commands/varienos/agentic-workflow/task-hunter.skeletonWrote 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-hunter.skeleton)<a href="https://agentmods.dev/commands/varienos/agentic-workflow/task-hunter.skeleton"><img src="https://agentmods.dev/badge/commands/varienos/agentic-workflow/task-hunter.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-hunter.skeleton"><img src="https://agentmods.dev/badge/commands/varienos/agentic-workflow/task-hunter.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 | $0.07007 |
| Opus 5.5 | $0.00000 | $0.02803 |
| Sonnet 5.5 | $0.00000 | $0.01401 |
| Haiku 4.5 | $0.00000 | $0.00701 |
Grade A, and why
task-hunter.skeleton 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 25d 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.
How it starts
The opening of the file, as written. The whole thing — 770 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Hunter — Autonomous Task Application
Backlog retrieves tasks, analyzes them, applies them, tests them, and commits. Usage:
/task-hunter <number>,/task-hunter <keyword>,/task-hunter 3,5,8
Argument Resolution
The user's input is resolved according to the following rules:
| Input Type | Example | Behavior |
|---|---|---|
| Single number | 5 |
Retrieve task 5 with backlog task 5 --plain |
| Comma-separated numbers | 3,5,8 |
Iterate through each one sequentially (3 → 5 → 8) |
| Keyword | login page |
List all tasks with backlog task list --plain, regardless of title/description |
| Empty input | (none) | Select the first suitable task with backlog task list -s "To Do" --plain |
Multi-task mode: Each task's Step 1–7 repeat independently, except for errors in one task do not affect others.
Step 1 — Read and Claim Task
backlog task <id> --plain
Read the task details. Extract the following information:
- Title
- Description
- Acceptance criteria (AC)
- Priority
- Current status
Immediately claim the task:
backlog task edit <id> -s "In Progress"
RULE: If the task is already in the "Done" state, DO NOT TOUCH. Inform the user and stop. RULE: If the task is in the "In Progress" state, ask the user: continue or start from scratch?
Step 2 — Analysis and Planning
2.1 — Codebase Cleanup
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.
- 25d ago Changed · +7 lines a4c7f86d856b
- 1mo ago First seen · 763 lines · 0 tokens per session scan A 3420d00bdce5
task-hunter.skeleton is a command published in the GitHub repository varienos/agentic-workflow (59 stars, last pushed 25d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,007 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.
Other commands, from other repositories
luda
Invoke Luda, your Scrum Master, for board integrity — orphan work items, plan-vs-tracker divergence, Done-without-negative-criteria, parked-without-a-trigger — plus ticket creation and team orchestration.
max
Invoke Max, your Senior Product Owner for product vision, backlog management, user stories, and sprint planning.
team-review
Coordinate a multi-role review of the current change.
sm
Invoke Scrum Master for board integrity — orphan work items, plan-vs-tracker divergence, Done-without-negative-criteria, parked-without-a-trigger — plus ticket creation and team orchestration.
po
Invoke Product Owner for product vision, backlog management, user stories, and sprint planning.
anchors
List what each requirement tag anchors to (read-only).