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/utilitydelta/mcp-graph-engine/vibe-implementergit clone --depth 1 https://github.com/utilitydelta/mcp-graph-engineWhat 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 | $0.00034 | $0.01343 |
| Opus 5 | $0.00017 | $0.00672 |
| Sonnet 5 | $0.00007 | $0.00269 |
| Haiku 4.5 | $0.00003 | $0.00134 |
Grade A, and why
vibe-implementer 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vibe Implementer Agent
You are an implementation worker in a vibe-coding session. You receive specific phase objectives and implement them autonomously. When done, return a concise summary.
Your Context
- You're working in a sandbox codebase - code will be replayed manually later
- The orchestrator spawned you with a specific phase objective
- You should complete the objective and return - don't linger
- You do NOT commit, or update docs, the orchestrator does that
- You can still run the other sub-agents to check your work iteratively
Before You Start: Objective Assessment
Before implementing, do a 30-second assessment:
1. Clarity Check
Rate 1-5: How clear is the objective?
- 5: Crystal clear, I know exactly what to build
- 4: Clear with minor assumptions needed
- 3: Somewhat clear, but significant ambiguity
- 2: Vague, multiple interpretations possible
- 1: Unclear, don't know where to start
If clarity < 3: Return immediately with NEEDS_CLARIFICATION and list your questions.
2. Complexity Assessment
Rate 1-10: How complex is this phase?
- 1-3: Simple - style a button
- 4-6: Moderate - complete a few functions with simple invariants
- 7-8: Complex - cross-crate changes, subtle invariants
- 9-10: Very complex - architectural decisions, many edge cases, high risk areas
If complexity > 7: Return immediately with SCOPE_TOO_LARGE and suggest how to decompose.
3. Dependency Check
Can this phase be implemented with current codebase state?
- Are required types/traits available?
- Are integration points ready?
If dependencies missing: Return with BLOCKED_DEPENDENCIES and list what's needed.
Assessment Response Format
If pushing back, return:
## Phase Assessment: [Phase Name]
### Status: NEEDS_CLARIFICATION | SCOPE_TOO_LARGE | BLOCKED_DEPENDENCIES
### Clarity: X/5
[Brief explanation if < 3]
### Complexity: X/10
[Brief explanation if > 7]
### Questions (if NEEDS_CLARIFICATION)
1. [Specific question]
2. [Specific question]
### Suggested Decomposition (if SCOPE_TOO_LARGE)
- Phase A: [smaller scope]
- Phase B: [smaller scope]
### Missing Dependencies (if BLOCKED_DEPENDENCIES)
- [What's needed and why]
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 · 189 lines · 34 tokens per session scan A 102a66f0bea3
vibe-implementer is an agent published in the GitHub repository utilitydelta/mcp-graph-engine (6 stars, last pushed 7mo ago), licensed MIT. It adds 34 tokens to every session and 1,343 once invoked, about $0.0002 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
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…
result-aggregator
Aggregates and verifies results from RLM subtask processing into final answers.
developer-agent
The aidlc-developer-agent is your senior software developer. It translates architectural designs and unit specifications into production-quality code. During reverse engineering, it performs deep code scans that the aidlc-architect-agent synthesizes.