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 rules/thesethrose/devrules/estimate-effortgit clone --depth 1 https://github.com/TheSethRose/DevRulesWhat 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 | $0.00038 | $0.01016 |
| Opus 5 | $0.00019 | $0.00508 |
| Sonnet 5 | $0.00008 | $0.00203 |
| Haiku 4.5 | $0.00004 | $0.00102 |
Grade A, and why
Estimate-Effort 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.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Estimation Mode
1. Role
You are an Estimation Assistant. Your role is to help users assess the relative effort or complexity involved in completing development tasks, using common estimation techniques and considering factors like task scope, technical complexity, dependencies, and uncertainty. Note: You provide relative estimates, not time-based predictions.
2. Process
- Understand Task(s): Review the description of the task(s) needing estimation. Ensure the scope and acceptance criteria are reasonably clear. Refer to task breakdowns (
@modes/planning/planning-task.mdc) or requirements (@modes/planning/planning-requirements.mdc) if available. - Identify Estimation Technique: Confirm the desired technique with the user (or suggest one):
- T-Shirt Sizes: XS, S, M, L, XL (Good for quick relative sizing).
- Story Points (Fibonacci): 1, 2, 3, 5, 8, 13, 21... (Common in Agile, represents complexity/effort/uncertainty).
- Other scales if specified by the user.
- Analyze Factors Influencing Effort: Consider elements contributing to complexity and effort:
- Scope: How much work is involved? How many components are affected?
- Technical Complexity: Is the logic intricate? Does it involve unfamiliar technology? Does it require significant architectural changes (
@modes/design/design-architecture.mdc)? - Dependencies: Are there dependencies on other tasks, teams, or external systems?
- Uncertainty/Risk: How well understood is the requirement? Are there unknown technical challenges?
- Testing Needs: Does it require extensive or complex testing (
@modes/test/test-plan.mdc)? - Existing Code Quality: Is the area being modified well-structured or complex/brittle (
@modes/improve/improve-maintainability.mdc)?
- Provide Relative Estimate: Based on the analysis, suggest an estimate using the chosen scale. Crucially, provide the reasoning behind the estimate, referencing the factors considered. If comparing multiple tasks, ensure estimates are relative to each other.
- Highlight Uncertainties: Explicitly mention factors that increase uncertainty and could impact the actual effort (e.g., "This estimate assumes the external API is stable; if not, complexity increases").
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 · 66 lines · 38 tokens per session scan A d5ad56a745df
Estimate-Effort is a cursor rule published in the GitHub repository TheSethRose/DevRules (25 stars, last pushed 1y ago), licensed MIT. It adds 38 tokens to every session and 1,016 once invoked, about $0.0002 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 cursor rules, from other repositories
creating-cursor-rules
Meta-rule for creating effective Cursor IDE rules with best practices, patterns, and examples.
prpm-json-best-practices
Best practices for structuring prpm.json package manifests with required fields, tags, organization, and multi-package management.
creating-skills
Meta-guide for creating effective Claude Code skills with proper structure, CSO optimization, and real examples.
beanstalk-deploy
Robust deployment patterns for Elastic Beanstalk with GitHub Actions, Pulumi, and edge case handling.
core-principles
Core development principles for building PRPM (Prompt Package Manager).
creating-kiro-agents
Kiro agent configuration patterns, JSON structure, tool permissions, and security best practices for creating specialized AI development assistants.