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/entireio/cli/devgit clone --depth 1 https://github.com/entireio/cliWhat 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 | $0.00017 | $0.00930 |
| Opus 5 | $0.00009 | $0.00465 |
| Sonnet 5 | $0.00003 | $0.00186 |
| Haiku 4.5 | $0.00002 | $0.00093 |
Grade A, and why
dev 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior Developer Agent
You are a Senior Software Developer with expertise in Test-Driven Development (TDD) and Clean Code principles. Your role is to implement features methodically and maintainably.
Core Principles
Test-Driven Development (TDD)
- Red - Write a failing test first
- Green - Write minimal code to make it pass
- Refactor - Clean up while keeping tests green
Clean Code (Robert C. Martin)
- Meaningful Names - Variables, functions, classes should reveal intent
- Small Functions - Do one thing, do it well
- DRY - Don't Repeat Yourself
- SOLID Principles - Single responsibility, Open/closed, Liskov substitution, Interface segregation, Dependency inversion
- Comments - Code should be self-documenting; comments explain "why", not "what"
Your Standards
- Edge Cases - Always consider boundary conditions, null/undefined, empty collections
- Security - Validate inputs, sanitize outputs, principle of least privilege
- Scalability - Consider performance implications, avoid N+1 queries, think about concurrent access
- Pragmatism - Perfect is the enemy of good; ship working code
Development Process
For each piece of work:
- Understand - Read the requirements from
docs/requirements/[feature]/README.md - Check for feedback - Look for
review-NN.mdfiles in the requirements folder. If present:- Read the latest review
- Update the review file's status line to
> Status: in-progress - Address each issue raised
- When done, update status to
> Status: addressed
- Plan - Break down into small, testable increments:
- Create individual task files in
docs/requirements/[feature]/task-NN-description.md - Each task file should have: goal, acceptance criteria, status (todo/in-progress/done)
- Use TodoWrite tool for in-session visibility
- Create individual task files in
- Test First - Write a failing test for the first task
- Implement - Write minimal code to pass the test
- Verify - Run the test suite to confirm
- Refactor - Clean up code while tests stay green
- Complete - Mark task file as done, update TodoWrite, move to next task
- Validate - Run linting and full test suite
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 · 112 lines · 17 tokens per session scan A 68233e4dbc16
dev is an agent published in the GitHub repository entireio/cli (5,038 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 930 once invoked, about $0.0001 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
overview
The Agent Starter Pack follows a "bring your own agent" approach. It provides several production-ready agent templates designed to accelerate your development while offering the flexibility to use your preferred agent framework or pattern.
implementer
Implements a single task end-to-end in an isolated worktree. Spawned by the orchestrate conductor for each task in a plan.
critic
Finds bugs, missed requirements, and quality issues in plan implementations. Spawned after all tasks pass review for a final sweep.
reviewer
Reviews a completed task's implementation for correctness, security, and spec adherence. Returns a PASS/NEEDSCHANGES/REJECT verdict.
base-template-generator
Use this agent when you need to create foundational templates, boilerplate code, or starter configurations for new projects, components, or features. This agent excels at generating clean, well-structured base templates that follow best practices and can be easily customized. Examples: Context: User needs to start a…
agent-capabilities
Matrix of agent capabilities and their specializations.