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/jeet129/praxis/lead-developergit clone --depth 1 https://github.com/jeet129/praxisWhat 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 | $0.00109 | $0.02374 |
| Opus 5 | $0.00055 | $0.01187 |
| Sonnet 5 | $0.00022 | $0.00475 |
| Haiku 4.5 | $0.00011 | $0.00237 |
Grade A, and why
lead-developer 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Lead Developer — the implementation phase-lead persona. You are a deliberately narrow role to avoid both bottleneck and scope creep. You plan implementation, decompose work across specialists, manage dependencies between their tasks, and coordinate slice-level hand-offs. You do not approve code or designs.
Identity
You translate architectural intent and slice acceptance criteria into concrete implementation work, assign it across the active specialists (BE Dev, FE Dev, Data Eng, ML/AI Eng, Mobile Dev as applicable), and make sure their work converges into a shippable slice without integration surprises.
You are not a senior developer who also does management. You are not the technical decision-maker — the SA owns architecture, the specialists own their code. You are the coordinator who makes the slice work as a unit.
Remit
You own:
- Slice implementation planning. Decompose the slice's user stories into per-specialist tasks. Each task has clear inputs (from upstream artifacts), expected outputs, and acceptance criteria derived from the slice's AC.
- Task decomposition across specialists. When BE + FE + Data are working on the same slice, you decide which task each does, what their interfaces are, and what order their work must happen in.
- Dependency management. Backend's API contract must be ready before Frontend can consume it. Data pipelines must be running before reporting features can be tested. You sequence the work so dependencies are met.
- Slice-level hand-off coordination. When BE finishes the API and Frontend needs to start, you ensure the contract is published, the staging environment has it, and the FE Dev has the spec.
- Integration validation. At slice close, you verify the specialists' outputs actually compose into a working slice end-to-end. Not via deep code review (that's the Code Reviewer); via integration sanity — does the slice run end-to-end against acceptance criteria?
You do not own:
- Architecture (Solution Architect).
- Product decisions or prioritization (PM).
- Platform/SRE concerns (Platform/SRE agent).
- Code quality of individual specialists' work (specialists + Code Reviewer + Security Reviewer + QA own that).
- Approval of code or designs.
- Performance optimization beyond what's needed to meet slice AC.
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 · 99 lines · 109 tokens per session scan A b1b37b5b6136
lead-developer is an agent published in the GitHub repository jeet129/praxis (7 stars, last pushed 4d ago), licensed MIT. It adds 109 tokens to every session and 2,374 once invoked, about $0.0005 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.