# Agentica Prompts

> Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity

- **Type:** Skill
- **Install:** `agentstack add skill-parcadei-continuous-claude-v3-agentica-prompts`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [parcadei](https://agentstack.voostack.com/s/parcadei)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [parcadei](https://github.com/parcadei)
- **Source:** https://github.com/parcadei/Continuous-Claude-v3/tree/main/.claude/skills/agentica-prompts

## Install

```sh
agentstack add skill-parcadei-continuous-claude-v3-agentica-prompts
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Agentica Prompt Engineering

Write prompts that Agentica agents reliably follow. Standard natural language prompts fail ~35% of the time due to LLM instruction ambiguity.

## The Orchestration Pattern

Proven workflow for context-preserving agent orchestration:

```
1. RESEARCH (Nia)     → Output to .claude/cache/agents/research/
       ↓
2. PLAN (RP-CLI)      → Reads research, outputs .claude/cache/agents/plan/
       ↓
3. VALIDATE           → Checks plan against best practices
       ↓
4. IMPLEMENT (TDD)    → Failing tests first, then pass
       ↓
5. REVIEW (Jury)      → Compare impl vs plan vs research
       ↓
6. DEBUG (if needed)  → Research via Nia, don't assume
```

**Key:** Use Task (not TaskOutput) + directory handoff = clean context

## Agent System Prompt Template

Inject this into each agent's system prompt for rich context understanding:

```
## AGENT IDENTITY

You are {AGENT_ROLE} in a multi-agent orchestration system.
Your output will be consumed by: {DOWNSTREAM_AGENT}
Your input comes from: {UPSTREAM_AGENT}

## SYSTEM ARCHITECTURE

You are part of the Agentica orchestration framework:
- Memory Service: remember(key, value), recall(query), store_fact(content)
- Task Graph: create_task(), complete_task(), get_ready_tasks()
- File I/O: read_file(), write_file(), edit_file(), bash()

Session ID: {SESSION_ID} (all your memory/tasks scoped here)

## DIRECTORY HANDOFF

Read your inputs from: {INPUT_DIR}
Write your outputs to: {OUTPUT_DIR}

Output format: Write a summary file and any artifacts.
- {OUTPUT_DIR}/summary.md - What you did, key findings
- {OUTPUT_DIR}/artifacts/ - Any generated files

## CODE CONTEXT

{CODE_MAP}   tuple[Path, Path]:
    """Return (input_dir, output_dir) for an agent."""
    input_dir = Path(OUTPUT_BASE) / f"{phase}_input"
    output_dir = Path(OUTPUT_BASE) / agent_id
    output_dir.mkdir(parents=True, exist_ok=True)
    return input_dir, output_dir

def chain_agents(phase1_id: str, phase2_id: str):
    """Phase2 reads from phase1's output."""
    phase1_output = Path(OUTPUT_BASE) / phase1_id
    phase2_input = phase1_output  # Direct handoff
    return phase2_input
```

## Anti-Patterns

| Pattern | Problem | Fix |
|---------|---------|-----|
| "Tell me what X contains" | May summarize or hallucinate | "Return the exact text" |
| "Check the file" | Ambiguous action | Specify RETRIEVE or VERIFY |
| Question form | Invites generation | Use imperative "RETRIEVE" |
| "Read and confirm" | May just say "confirmed" | "Return the exact text" |
| TaskOutput for handoff | Floods context with transcript | Directory-based handoff |
| "Be thorough" | Subjective, inconsistent | Specify exact output format |

## Expected Improvement

- Without fixes: ~60% success rate
- With RETRIEVE + explicit return: ~95% success rate
- With structured tool schemas: ~98% success rate
- With directory handoff: Context preserved, no transcript pollution

## Code Map Injection

Use RepoPrompt to generate code map for agent context:

```bash
# Generate codemap for agent context
rp-cli --path . --output .claude/cache/agents/codemap.md

# Inject into agent system prompt
codemap=$(cat .claude/cache/agents/codemap.md)
```

## Memory Context Injection

Explain the memory system to agents:

```
## MEMORY SYSTEM

You have access to a 3-tier memory system:

1. **Core Memory** (in-context): remember(key, value), recall(query)
   - Fast key-value store for current session facts

2. **Archival Memory** (searchable): store_fact(content), search_memory(query)
   - FTS5-indexed long-term storage
   - Use for findings that should persist

3. **Recall** (unified): recall(query)
   - Searches both core and archival
   - Returns formatted context string

All memory is scoped to session_id: {SESSION_ID}
```

## References

- ToolBench (2023): Models fail ~35% retrieval tasks with ambiguous descriptions
- Gorilla (2023): Structured schemas improve reliability by 3x
- ReAct (2022): Explicit reasoning before action reduces errors by ~25%

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [parcadei](https://github.com/parcadei)
- **Source:** [parcadei/Continuous-Claude-v3](https://github.com/parcadei/Continuous-Claude-v3)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-parcadei-continuous-claude-v3-agentica-prompts
- Seller: https://agentstack.voostack.com/s/parcadei
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.