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.
git clone --depth 1 https://github.com/thapaliyabikendra/ai-artifactsWrote 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/thapaliyabikendra/ai-artifacts/add-feature-modes)<a href="https://agentmods.dev/commands/thapaliyabikendra/ai-artifacts/add-feature-modes"><img src="https://agentmods.dev/badge/commands/thapaliyabikendra/ai-artifacts/add-feature-modes/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/commands/thapaliyabikendra/ai-artifacts/add-feature-modes"><img src="https://agentmods.dev/badge/commands/thapaliyabikendra/ai-artifacts/add-feature-modes.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 | $0.00000 | $0.02029 |
| Opus 5 | $0.00000 | $0.01014 |
| Sonnet 5 | $0.00000 | $0.00406 |
| Haiku 4.5 | $0.00000 | $0.00203 |
Grade A, and why
add-feature-modes 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 9d 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Feature - Execution Modes
Detailed execution scripts for each mode of the /add-feature command.
Execution: --minimal Mode
For simple CRUD features, skip documentation and use direct scaffolding.
Use Task tool with subagent_type="abp-developer" and model="sonnet":
Implement CRUD feature for {feature-name}.
Requirements: {requirements-text}
Context: Read CLAUDE.md, docs/architecture/README.md
Skills: Apply abp-framework-patterns, efcore-patterns, fluentvalidation-patterns
Generate ALL files in a single pass:
1. Entity in Domain layer
2. DTOs in Application.Contracts
3. AppService interface + implementation
4. FluentValidation validator
5. EF Core configuration
6. Permissions
Build and verify: dotnet build api/*.slnx
Output: List created files. Done.
Execution: --fast Mode
Skip business-analyst when requirements are detailed. Backend-architect parses requirements directly.
Step 1: Design + Contracts
Use Task tool with subagent_type="backend-architect", model="haiku":
Create technical design AND generate contracts for {feature-name}.
Requirements (parse directly): {requirements-text}
Context: Read CLAUDE.md, docs/architecture/README.md, docs/domain/permissions.md
Skills: Apply technical-design-patterns, abp-contract-scaffolding
Output:
1. docs/features/{feature-name}/technical-design.md (max 150 lines)
2. docs/domain/entities/{entity}.md (entity definition)
3. Application.Contracts/{Feature}/I{Entity}AppService.cs
4. Application.Contracts/{Feature}/{Entity}Dto.cs
5. Application.Contracts/{Feature}/Create{Entity}Dto.cs
6. Application.Contracts/{Feature}/Update{Entity}Dto.cs
7. Application.Contracts/{Feature}/Get{Entity}sInput.cs
8. Application.Contracts/Permissions/{Entity}Permissions.cs
9. Update docs/domain/permissions.md
Checkpoint: Contracts exist.
Step 2: Parallel Implementation + Testing
Launch BOTH agents simultaneously using multiple Task tool calls in ONE message:
Agent A - Task with subagent_type="abp-developer", model="sonnet":
Implement {feature-name} using generated contracts.
Input: Application.Contracts/{Feature}/ (interface + DTOs exist)
Skills: Apply abp-framework-patterns, efcore-patterns, fluentvalidation-patterns
Generate:
1. Domain/{Feature}/{Entity}.cs
2. Domain.Shared/{Feature}/{Entity}Consts.cs
3. Application/{Feature}/{Entity}AppService.cs
4. Application/{Feature}/{Entity}ApplicationMappers.cs
5. Application/{Feature}/*Validator.cs
6. EntityFrameworkCore/EntityTypeConfigurations/{Entity}Configuration.cs
7. Update DbContext, PermissionDefinitionProvider
DO NOT recreate contracts - they exist.
Build: dotnet build api/*.slnx
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.
- 9d ago First seen · 261 lines · 0 tokens per session scan A 73fe0d110d17
add-feature-modes is a command published in the GitHub repository thapaliyabikendra/ai-artifacts (24 stars, last pushed 5mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,029 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.