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 scope-managementgit 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/scope-management)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/scope-management"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/scope-management/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/scope-management"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/scope-management.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 | $0.00033 | $0.00809 |
| Opus 5.5 | $0.00013 | $0.00324 |
| Sonnet 5.5 | $0.00007 | $0.00162 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
scope-management 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope Management
Overview
Scope is defended by what you write DOWN, especially the "out of scope" line. Undocumented scope drifts; a task whose AC quietly grows mid-flight is the classic cause of a blown estimate and a bounced UAT.
Core principle: Name the boundary explicitly. New scope becomes a new task, never an edit to an in-progress one.
For every feature, write
- In scope: concrete deliverables in this iteration.
- Out of scope: explicitly named items deferred or excluded — this line does the real work.
- Assumptions: constraints treated as given.
TaskTrooper has no epic. For a single direct task, this lives in its own description. For a feature that spans several tasks via analiz, it lives on the analiz task (description or add_task_document) — never re-written per implementation task.
Mid-flight expansion
When a request grows while work is in progress: create a new task for the expansion. Do NOT edit the AC of an in-progress task — a moving target invalidates the developer's plan and QA's scenarios and silently inflates the estimate.
Except when the human changes the task themselves. A comment the task's owner writes ON the task ("also show the logos in the marquee"), or their own edit of its description or criteria, is not mid-flight expansion to push back on — it is the task's requirement now. It outranks the original description and its out-of-scope list; every role builds, reviews, tests and accepts against it. Do not split it into a new task or treat it as creep unless the human asks for that.
MoSCoW inside a feature
Must → this task's acceptance_criteria. Should/Could → separate backlog tasks, never folded into this one. Won't → the Out of scope line, with a reason (see backlog-prioritization).
Dropping a criterion deliberately
Use cancel_criterion with a reason when a criterion is descoped, superseded by a later human comment, or moved to another task — never to get past work that simply wasn't done. cancel_criterion says "we're not shipping this here," which is a scope decision; a rejected review_criterion says "this doesn't work yet," which is a defect. Don't use one for the other.
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 · 59 lines · 33 tokens per session scan A 3cf64d082b2a
scope-management is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 33 tokens to every session and 809 once invoked, about $0.0001 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.