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 commands/mort-lab/excel-mcp/hackathon-prp-parallelgit clone --depth 1 https://github.com/mort-lab/excel-mcpWhat 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 | $0.00014 | $0.02539 |
| Opus 5 | $0.00007 | $0.01269 |
| Sonnet 5 | $0.00003 | $0.00508 |
| Haiku 4.5 | $0.00001 | $0.00254 |
Grade A, and why
hackathon-prp-parallel 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 — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hackathon PRP Parallel Workflow - Maximum Speed Edition
Execute a massive parallel workflow that leverages multiple AI agents working simultaneously to deliver a complete solution in record time.
Overview
This workflow deploys 20+ parallel agents:
- 5 agents for spec generation (different perspectives)
- 5 agents for prompt plan creation
- 5 agents for backend implementation
- 5 agents for frontend implementation
- 2 agents for integration and demo prep
All agents work concurrently and report results for synthesis.
Step 1: Parallel Spec Generation (5 minutes)
Deploy 5 parallel agents to analyze the challenge from different angles:
Use the Task tool to run these 5 research agents in PARALLEL for challenge: $ARGUMENTS
Task 1 - Technical Architecture Agent:
"Analyze {{challenge}} and create technical architecture spec:
- System design and components
- Technology choices and justification
- API design patterns
- Database schema design
- Performance considerations
- Security architecture
Save to: PRPs/specs/{{challenge|slugify}}-tech-spec.md"
Task 2 - User Experience Agent:
"Analyze {{challenge}} from UX perspective:
- User journeys and flows
- UI component requirements
- Interaction patterns
- Accessibility requirements
- Error handling UX
- Loading and feedback states
Save to: PRPs/specs/{{challenge|slugify}}-ux-spec.md"
Task 3 - Business Logic Agent:
"Define business rules and logic for {{challenge}}:
- Core business rules
- Validation requirements
- Edge cases and exceptions
- Data integrity rules
- Business process flows
- Integration requirements
Save to: PRPs/specs/{{challenge|slugify}}-business-spec.md"
Task 4 - Testing Strategy Agent:
"Create comprehensive testing strategy:
- Test scenarios and cases
- Performance test requirements
- Security test cases
- Integration test approach
- Demo test scenarios
- Coverage targets
Save to: PRPs/specs/{{challenge|slugify}}-test-spec.md"
Task 5 - Demo Impact Agent:
"Analyze for maximum demo impact:
- Key features to highlight
- Wow factors to implement
- Metrics to showcase
- Story narrative
- Backup plans
- Time allocations
Save to: PRPs/specs/{{challenge|slugify}}-demo-spec.md"
Synthesize all specs into: PRPs/specs/{{challenge|slugify}}-unified-spec.md
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 · 413 lines · 14 tokens per session scan A 5e026c41416f
hackathon-prp-parallel is a command published in the GitHub repository mort-lab/excel-mcp (5 stars, last pushed 25d ago), licensed MIT. It adds 14 tokens to every session and 2,539 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 commands, from other repositories
implement
yes, thank you! please proceed with implementation.
suggest-solution
if there is better solution, please suggest it.
create-forwarding-rule
Create a ZPA client forwarding policy rule to bypass or intercept traffic.
auto
AI auto strategy executor. Analyzes task and automatically selects and executes the best strategy: direct execution, hybrid-auto PRD generation, hybrid-worktree isolated development, or mega-plan multi-feature orchestration.
spec-plan
Run a resumable spec interview to produce spec.json/spec.md (planning-time), then optionally compile to prd.json. Usage: /plan-cascade:spec-plan " " [--output-dir ] [--flow ] [--first-principles] [--max-questions N] [--feature-slug ] [--compile] [--tdd ] [--confirm] [--no-confirm].
adops-audit
Multi-dimensional GAM audit: delivery health, inventory hygiene, security baseline, creative compliance, billing alignment. Read-only and free.