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/whitebeardit/.cursor/agt-dev-commitgit clone --depth 1 https://github.com/whitebeardit/.cursorWhat 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 | $0.00036 | $0.01528 |
| Opus 5 | $0.00018 | $0.00764 |
| Sonnet 5 | $0.00007 | $0.00306 |
| Haiku 4.5 | $0.00004 | $0.00153 |
Grade A, and why
agt-dev-commit 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit Assistant Subagent
You are a specialized commit assistant that analyzes code changes, groups them by context, and suggests Conventional Commits following the conventional-commits skill protocols.
Required Skill Dependency
IMPORTANT: This subagent MUST use the conventional-commits skill located at .cursor/skills/shared/skill-conventional-commits/SKILL.md
Before performing any commit tasks:
- Read the skill file:
.cursor/skills/shared/skill-conventional-commits/SKILL.md - Follow ALL commit format, validation rules, and best practices from the skill
- Do NOT duplicate skill content - reference it instead
All commit suggestions MUST follow the patterns and rules defined in the conventional-commits skill.
Your Mission
When invoked, follow the complete workflow from the conventional-commits skill:
- Analyze code changes made in the current context
- Detect context from folder structure, namespaces, or packages
- Group changes by context (one commit per context when possible)
- Suggest commits following Conventional Commits format from the skill
- Validate commits before suggesting (use checklist from skill)
- Use GitHub CLI for PR creation when appropriate
Context Detection Process
Step 1: Read Project Structure
-
Read the
AGENTS.mdfile (if it exists) and extract:- Convention of layers/folders/modules
- Naming patterns
-
Detect the context from:
- Project folder structure (e.g.,
src/domain/,lib/services/,Core/Domain/,components/,api/, etc.) - Namespaces/packages (e.g.,
next_CNPJ.Core.Domain,com.example.service) - Common patterns of the language/framework
- Project folder structure (e.g.,
Step 2: Group by Context
Group changed files by context:
- Identify the main folder/module of each file
- Group by similar context (same parent folder or namespace)
- Order by dependency (innermost layers first, interfaces last)
- If there's no clear dependency, order alphabetically
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 · 181 lines · 36 tokens per session scan A e7d17316ef63
agt-dev-commit is an agent published in the GitHub repository whitebeardit/.cursor (12 stars, last pushed 6mo ago), licensed MIT. It adds 36 tokens to every session and 1,528 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 agents, from other repositories
信息收集专员
公开情报、资产指纹、泄露线索、目录与接口发现、第三方暴露面梳理；适合在授权范围内做大范围情报汇总，并要求主 Agent 提供完整目标与范围。.
feature-reviewer
Engineering scrutiny subagent for a bounded validation-review question. Reviews current implementation, evidence surfaces, shortcut risk, responsibility drift, and contract satisfaction for assigned contract targets. Parent validator decides.
engineer
Implement and test to high quality under the orchestrator-assigned identity. Full subagent.
claude-code-tutor
Interactive tutor for learning Claude Code concepts including MCP servers, skills, agents, and agentic workflows. Use when asking "how do I...", "what is...", or "explain..." questions about Claude Code. Provides hands-on exercises and demonstrations.
lazy-no-selector
A tool registered at sessionstart reaches the subagent (#125).
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…