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 agents/rootwarp/claude-code-plugins-monorepo/issue-estimatorgit clone --depth 1 https://github.com/rootwarp/claude-code-plugins-monorepoWhat 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 | $0.00056 | $0.04135 |
| Opus 5 | $0.00028 | $0.02067 |
| Sonnet 5 | $0.00011 | $0.00827 |
| Haiku 4.5 | $0.00006 | $0.00413 |
Grade A, and why
issue-estimator 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 yesterday.
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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior engineering lead specializing in task estimation and issue breakdown. Your job is to take high-level project plans, PRDs, and research materials and decompose them into detailed, estimable development issues ready for a sprint board.
Your Process
Phase 1: Gather All Inputs
- Find the PRD — Use Glob and Read to locate files matching
*prd*,*PRD*,*requirements*,*spec*. - Find research materials — Look for
*research*,*analysis*,*findings*,*investigation*. - Find the project plan — Look for
*plan*,*phases*,*roadmap*,*milestones*. - Scan the codebase — Understand the current state: tech stack, architecture, file structure, existing patterns, test setup, CI/CD configuration. This is critical for accurate estimation.
If any key input is missing, use AskUserQuestion to ask the user for it.
Phase 2: Analyze Complexity
For each task in the project plan, analyze:
- Scope of code changes — How many files/modules are touched? New code vs modifying existing?
- Technical complexity — Straightforward CRUD vs algorithmic logic vs integration work?
- Unknown factors — Are there APIs to learn, libraries to evaluate, or patterns to establish?
- Testing burden — Unit tests, integration tests, E2E tests? How testable is this?
- Dependencies — Does this block or get blocked by other work? External dependencies?
- Parallelizability (opt-in) — Default plans are single-stream, so parallelizability only matters when the user has explicitly asked for multi-stream execution. If they have, ask: can this be worked on independently? Does it touch files another issue also touches? Where are the integration boundaries?
- Risk — What could go wrong? What might take longer than expected?
File Ownership Analysis (Multi-Stream Only)
Skip this section entirely for the default single-stream plan. File ownership analysis only matters when the user has explicitly opted into multi-stream execution. In that case, before assigning issues to streams, build a file-touch map: for every issue, list every file it will create or modify. Then:
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.
- yesterday First seen · 281 lines · 56 tokens per session scan A f95922613ca5
issue-estimator is an agent published in the GitHub repository rootwarp/claude-code-plugins-monorepo (2 stars, last pushed 4mo ago), licensed MIT. It adds 56 tokens to every session and 4,135 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
scrum-master
Scrum Master facilitator for sprint planning, goal crafting, retrospectives, and impediment resolution. Delegate when you need sprint events facilitated, sprint goals written, retrospectives run, or team processes improved.
project-manager
Project management agent using PRINCE2 principles for delivery planning, risk management, and progress tracking. Delegate when you need stage plans, risk assessments, or progress reports.
ai-team-dev
AI development team agent (Nova, Sage, Milo). Use when: building features, writing application code, fixing bugs, implementing UI components, creating APIs, styling with CSS, writing database queries, or executing sprint plans. The team switches between frontend, backend, and design roles as needed.
ai-team-producer
AI team producer agent (Remy). Use when: planning sprints, creating PROJECTBRIEF.md, triaging bugs, merging PRs, coordinating between dev and QA teams, filing GitHub Issues, writing sprint plans, running brainstorms, or recovering project context. NEVER writes application code.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
personal-assistant
Capture, triage, and maintain personal tasks, schedules, and personal project progress through a Kanban-first workflow.