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 commands/manavsehgal/vibesolver/sprintgit clone --depth 1 https://github.com/manavsehgal/vibesolverWrote 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/manavsehgal/vibesolver/sprint)<a href="https://agentmods.dev/commands/manavsehgal/vibesolver/sprint"><img src="https://agentmods.dev/badge/commands/manavsehgal/vibesolver/sprint.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00430 |
| Opus 5 | $0.00000 | $0.00215 |
| Sonnet 5 | $0.00000 | $0.00086 |
| Haiku 4.5 | $0.00000 | $0.00043 |
Grade A, and why
sprint 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 3d 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.
What it actually says
Ultrathink to generate the next VibeSolver project sprint using this streamlined approach:
-
ANALYSIS PHASE:
- IMPORTANT: Read and follow the @specs/ folder for understanding the product vision, design requirements, technical stack, and roadmap if it exists.
- IMPORTANT: Prioritize any features mentioned incomplete in the roadmap.
- Review files in sprints/ folder if it exists to understand progression and numbering
- Review the project code to understand the state of the project
- Review CLAUDE.md if available to understand code generation guidance
- For the first sprint focus on setting up the project scaffold, configurations, environment settings, virtual environment, installing dependencies, development and testing tooling
- IMPORTANT: For every subsequent sprint, follow end-to-end feature-slice approach (minimum viable product) based on the roadmap if it exists, which includes adequate frontend UI and backend capabilities to help user evaluate all features released in that sprint using the frontend UI.
- Determine the next sprint number and logical feature focus
-
PLANNING PHASE:
- Based on your analysis, draft a comprehensive sprint plan
- IMPORTANT: Follow test-driven development principles for development workflow
- IMPORTANT: Follow modularity, maintainability, extensibility, and single responsibility principles for code generation
- Include all required sections:
- Title with proper sprint number format (e.g., "Sprint 004: Feature Name")
- Overview explaining purpose and context
- Clear goals (3-5 bullet points)
- Detailed tasks with test examples
- Specific acceptance criteria
- Development instructions
- Ensure the sprint builds logically on previous work
- Verify the sprint delivers actual user value
-
OUTPUT:
- Save EXACTLY ONE file named '/sprints/[NUMBER]-[feature-name].md' where:
- [NUMBER] is the three-digit sprint number (e.g., '003', '004')
- [feature-name] briefly describes the focus area in kebab-case
- Confirm the file meets project standards and requirements before saving
- Save EXACTLY ONE file named '/sprints/[NUMBER]-[feature-name].md' where:
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.
- 3d ago First seen · 34 lines · 0 tokens per session scan A 4ceefea45533
sprint is a command published in the GitHub repository manavsehgal/vibesolver (5 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 430 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 2026-08-31.
Other commands, from other repositories
gtplanner-init
初始化 GTPlanner 环境并验证配置.
remote-autopilot-install.v1
Remotely install Stakpak Autopilot on any reachable Linux host over SSH, with optional AWS/GCP/Azure VM discovery or provisioning: /remote-autopilot-install.
planwt
You are the orchestrator for a bounded worktree task.
statuswt
You are checking the status of all active worktree task files in the project.
finishwt
You are finishing a worktree task.
echocoding
When user invokes this skill, follow this sequence.