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 skills add makifbaysal/tasktrooper --skill backlog-prioritizationgit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/skills/makifbaysal/tasktrooper/backlog-prioritization)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/backlog-prioritization"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/backlog-prioritization/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/skills/makifbaysal/tasktrooper/backlog-prioritization"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/backlog-prioritization.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 | $0.00055 | $0.00988 |
| Opus 5.5 | $0.00022 | $0.00395 |
| Sonnet 5.5 | $0.00011 | $0.00198 |
| Haiku 4.5 | $0.00006 | $0.00099 |
Grade A, and why
backlog-prioritization 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 8d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backlog Prioritization
Overview
Prioritization decides what agents pick up next. TaskTrooper is a local, single-user product with no usage data, so a scored framework with invented numbers (fake "Reach 200") is theatre. Order by the levers the board actually enforces, and fall back to an explicit estimate only when several same-level features genuinely need ranking.
Core principle: priority, blocked_by, deploy_depends_on and backlog/todo are the real order. Score only when they tie.
The real levers
| Lever | What it controls |
|---|---|
priority (critical / high / medium / low) |
The only persisted order field; sorts list_ready_tasks critical-first, then by age. |
blocked_by |
The enforced START order — a task parks in blocked while any listed task is open, and is picked up automatically when the last one lands. |
deploy_depends_on |
The enforced SHIP order — this task is not released until the listed ones are live. |
| backlog vs todo | The human gate — nothing in backlog is picked up; moving to todo starts it. |
Priority ladder
- critical — data loss or corruption, a security exposure, the product unusable, a broken release.
- high — a core flow broken, a regression of shipped behaviour, an analiz that unblocks two or more tasks, a stated deadline.
- medium — default for a requested feature.
- low — cosmetic, nice-to-have, a Should/Could split-off from MoSCoW.
Within a level: the stakeholder's stated order, then unblockers (an analiz or a backend task other work depends on), then smaller work first.
MoSCoW inside a feature
When scoping one feature or task:
- Must → this task's
acceptance_criteria. - Should / Could → separate backlog tasks, not folded into this one's criteria.
- Won't → the
description's Out of Scope line, with the reason.
RICE/ICE — only for an explicit "what's next" call
Use a lightweight score only when the stakeholder asks "what should we do next" across three or more same-priority-level features, and label every factor as an estimate with its basis — never invent a reach number with no usage data behind it.
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.
- 8d ago First seen · 67 lines · 55 tokens per session scan A 803064f6de41
backlog-prioritization is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 55 tokens to every session and 988 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-05.
Other skills, from other repositories
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
paperclip
Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.
paperclip-board
Manage a Paperclip company as a board member via chat. Use when the user wants onboarding, company or agent management, approvals, task monitoring, cost oversight, or work product review in the Paperclip control plane.
paperclip-distill
Use when an operation issue is a Paperclip cursor-window, distill, or backfill. Turn source-bundled Paperclip activity into wiki-insightful project standups, durable project pages, decisions, and history without asset dereferencing.
summarize-status
Write a short, colloquial summary for a Paperclip summary slot: open with the 1–3 specific, concrete actions the reader needs to take right now to unblock the work, then a brief plain-language status, streaming progress as it works.
paperclip-task-bridge
Create, comment on, update, and list Paperclip tasks from Hermes using scoped Paperclip API credentials.