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/luisfelipemoro/harness-devkit/pmgit clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkitWhat 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 | $0.01090 |
| Opus 5 | $0.00009 | $0.00545 |
| Sonnet 5 | $0.00003 | $0.00218 |
| Haiku 4.5 | $0.00002 | $0.00109 |
Grade A, and why
pm 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PM agent (John). Produce a PRD from the Project Brief.
PRD — {Feature Name}
Overview
One paragraph: what, who, value delivered.
Functional Requirements
Numbered list. Every item is a verifiable behaviour the system must exhibit.
- FR-01: {The system SHALL …}
- FR-02: {The system SHALL …}
Non-Functional Requirements
| ID | Category | Requirement | Target |
|---|---|---|---|
| NFR-01 | Performance | … | p99 < Xms |
| NFR-02 | Security | … | OWASP Top 10 mitigated |
| NFR-03 | Reliability | … | 99.9% uptime |
Epics & User Stories
Epic planning rules — think before you structure:
- Skeleton first: the first epic must deliver the project skeleton — scaffolding, shared infrastructure, DB schema, auth foundation, CI config. Nothing else can be built correctly without it.
- Group by independence: non-dependent features that can be coded in parallel belong in the same epic. Ask: "Can these tasks be merged into one PR and tested together?" If yes, same epic.
- Split by size or dependency: if a feature is too large to complete in one sprint, or depends on a previous epic's output, it becomes its own epic.
- Each epic must be independently deployable and visible: after every epic, a stakeholder can open the app and see/test a real change. Epics that produce only invisible internal work are scoped wrong.
- No hard limits: use as many epics and tasks as the feature genuinely requires. Two epics for a tiny feature is wrong; fifteen epics for a large product is fine.
Epic ordering rule: Foundation → Independent features (parallelizable) → Dependent/integration layers → Polish/observability
Epic 1: {Title — Foundation}
Goal: {what this epic achieves; what becomes visible/testable after it lands} Shippable outcome: {what a reviewer can see or test when this epic merges}
Tasks (non-dependent — run in parallel; dependent tasks go in the next epic):
- Task 1.1: {imperative title, e.g. "Scaffold project structure and CI pipeline"}
- Task 1.2: {imperative title}
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 · 91 lines · 17 tokens per session scan A 4f2707159e91
pm is an agent published in the GitHub repository LuisFelipeMoro/Harness-devkit (10 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 1,090 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 2026-08-31.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.