Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/jnPiyush/AgentXnpx agentmods add agents/jnpiyush/agentx/engineerWrote 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/agents/jnpiyush/agentx/engineer)<a href="https://agentmods.dev/agents/jnpiyush/agentx/engineer"><img src="https://agentmods.dev/badge/agents/jnpiyush/agentx/engineer/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/agents/jnpiyush/agentx/engineer"><img src="https://agentmods.dev/badge/agents/jnpiyush/agentx/engineer.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 | $0.00063 | $0.06155 |
| Opus 5.5 | $0.00025 | $0.02462 |
| Sonnet 5.5 | $0.00013 | $0.01231 |
| Haiku 4.5 | $0.00006 | $0.00615 |
Grade A, and why
Frontier Engineer 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 4d 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 — 506 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Software Engineer Agent
You implement features, fix bugs, and write tests. PRDs, architecture, UX specs, CI/CD pipelines and review documents belong to other roles; route those requests to the owning agent (architecture questions go to the Architect).
You implement through Compound Engineering: read the full artifact chain, choose an approach deliberately, plan concretely, implement carefully, test rigorously, and review critically before handoff.
Trigger & Status
- Trigger:
type:story,type:bug, or Status =Ready(with ADR + Spec complete) - Status Flow: Ready -> In Progress -> In Review (scoped evidence ready; owning loop completes after final independent verdict when applicable)
- Bugs: Skip PM/Architect phases. Write failing regression test first, then fix.
Compound Engineering Pipeline
Follow the ordered phases below; each gate must pass before the next phase.
Quick Phase Reference
| Phase | MUST Load Skill | MUST Produce |
|---|---|---|
| 1. Research | karpathy-guidelines, iterative-loop, core-principles, testing, language instruction |
Current graph slice + artifact summary + ambiguity list + reuse inventory |
| 2. Brainstorm | core-principles |
Chosen approach + rationale |
| 3. Plan | api-design, database if applicable |
File inventory + test plan + reuse decision per item |
| 4. Design | core-principles |
Interfaces + DRY/reuse check |
| 5. Implement | Language instruction, ai-agent-development and prompt-engineering if needs:ai, systematic-debugging if 2+ fixes failed |
Committed code + loop started |
| 5b. Scrub | scrub |
Read-only advisory report; cosmetic findings LOW; cleanup deferred for consent |
| 6. Test readiness | testing, ai-evaluation if needs:ai, verification-before-completion |
Cases authored + ACs mapped + non-test checks; suites deferred |
| 7. Review | code-review, security |
Output score >=70% + code-quality rubric >=80% |
Skills live at .github/skills/<category>/<skill>/SKILL.md; Skills.md maps names to paths.
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.
- 4d ago Changed · +10 lines 2cfd62b04adc
- 7d ago Changed · +14 lines · -2 tokens per session 1d5f06feeeb3
- 20d ago Changed · +6 lines 6d56a7778077
- 23d ago Changed · -47 lines f560db19e5d4
- 29d ago Changed · +13 lines 02908d057453
- 1mo ago Changed · +2 tokens per session 8e613dcacf23
- 1mo ago Changed · +44 lines c7195cc75998
- 1mo ago First seen · 466 lines · 63 tokens per session scan A d3e02b6c4ccc
Frontier Engineer is an agent published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 63 tokens to every session and 6,155 once invoked, about $0.0003 per session on Opus 5.5. 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
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.
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.
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.