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/echoingvesper/mcp-task-orchestrator/prp-base-executegit clone --depth 1 https://github.com/EchoingVesper/mcp-task-orchestratorWhat 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 | $0.00000 | $0.00731 |
| Opus 5 | $0.00000 | $0.00365 |
| Sonnet 5 | $0.00000 | $0.00146 |
| Haiku 4.5 | $0.00000 | $0.00073 |
Grade A, and why
prp-base-execute 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 3d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute Enhanced BASE PRP with Context Engineering
Implement a feature using the enhanced PRP file with security-first design and multi-stage validation.
PRP File: $ARGUMENTS
Pre-Execution Orchestrator Check
MANDATORY:
# Verify orchestrator connection
claude mcp list | grep task-orchestrator || (echo "FIXING ORCHESTRATOR..." && claude mcp restart task-orchestrator)
# If orchestrator fails, STOP and follow CLAUDE.md protocol
# DO NOT PROCEED without working orchestrator
Execution Process
-
Load Enhanced PRP
- Read the specified PRP file
- CRITICAL: Load referenced enhanced AI documentation from PRPs/ai_docs/
- Understand all context, requirements, and security considerations
- Follow all instructions including security-first design principles
- Ensure you have all context from ai_docs/, validation/, and patterns/
- Do additional research if needed, referencing context engineering guide
-
ULTRATHINK
- Ultrathink before you execute the plan. Create a comprehensive plan addressing all requirements.
- Break down the PRP into clear todos using the TodoWrite tool.
- Use agents subagents and batchtool to enhance the process.
- Important ENSURE CLEAR TASKS FOR SUBAGENTS WITH CONTEXT
- Each subagent MUST read the PRP and understand its context
- Identify implementation patterns from existing code to follow.
- Never guess about imports, file names funtion names etc, ALWAYS be based in reality and real context gathering
-
Execute the plan
- Execute the PRP step by step
- Implement all the code
- Use orchestrator_execute_task for complex subtasks
- Track progress with orchestrator_get_status
-
Enhanced Multi-Stage Validation
- Stage 1: Syntax & Security (ruff, mypy, bandit, safety)
- Stage 2: Unit Testing with Security Focus (XSS, injection, authorization tests)
- Stage 3: Integration & Database Testing (real component validation)
- Stage 4: Security & Performance Validation (audit, benchmarks)
- Stage 5: Production Readiness (end-to-end, deployment validation)
- Fix any failures at each stage before proceeding
- Reference PRPs/validation/ for detailed validation procedures
- Always re-read PRP and security requirements to ensure compliance
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.
- 3d ago First seen · 75 lines · 0 tokens per session scan A b737f259abdc
prp-base-execute is a command published in the GitHub repository EchoingVesper/mcp-task-orchestrator (28 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 731 tokens. 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 commands, from other repositories
screen-usecase
筛选、验证并撰写 OpenClaw 用例。输入来源 URL 或描述,输出适配评估或完整用例 PR。.
evolve
Agrupa instincts consolidados en skills accionables y las registra en skills-registry/custom/evolved/. Las skills quedan PENDIENTEREVISION hasta que el usuario las apruebe.
proyecto
Declara el proyecto activo (scope global) para atribucion de coste/horas en agentactions. Sin argumento, muestra el proyecto actual.
svsi-review
/svsi-review {slug} # modo interactivo en sesión Claude Code /svsi-review --batch {file} # delega a predrivereview.py (tmux, no en sesión) /svsi-review --stats # métricas acumuladas desde SQLite.
handover
Works for you. Go outside and live. — AI orchestrator that auto-routes tasks to the cheapest model that solves them. 70% run free on local models. Self-auditing, self-improving, zero prompting skill needed. Built with vibe coding by a finance student. Your models, your data.
instinct-status
Shows learned instincts from dqiii8.db, grouped by project and confidence. Internal diagnostic tool — not for user invocation.