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/majiayu000/vibeguard/plannergit clone --depth 1 https://github.com/majiayu000/vibeguardWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/majiayu000/vibeguard/planner)<a href="https://agentmods.dev/agents/majiayu000/vibeguard/planner"><img src="https://agentmods.dev/badge/agents/majiayu000/vibeguard/planner.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00031 | $0.00356 |
| Opus 5 | $0.00015 | $0.00178 |
| Sonnet 5 | $0.00006 | $0.00071 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
planner 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 today.
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.
What it actually says
Planner Agent
Responsibilities
Analyze user needs and generate a structured implementation plan. No coding, just planning.
Workflow
-
Understand the needs
- Read user descriptions and extract core goals and constraints
- Identify ambiguous points and list issues that need clarification
-
Explore existing code
- Use Grep/Glob to search for related files and patterns
- Understand the existing architecture, data flow, and dependencies
- Mark existing components that can be reused (VibeGuard L1: search first then write)
-
Generate plan
- List of steps sorted by risk/dependency
- Each step includes: what to change, why to change, which files are affected, and completion conditions
- Mark breaking changes and risk points
-
Output format
## Plan: <title>
### Target
<One sentence description>
### Constraints
- <constraint list>
### Steps
1. <Step> — Files: <files> — Completion criteria: <criteria>
2. ...
### Risk
- <Risk and Mitigation Measures>
### Don’t do it
- <Explicitly excluded>
VibeGuard Constraints
- Search for existing implementations before proposing new files or classes; cite useful reuse evidence without a required marker.
- No backward compatibility layer planned
- Do not plan additional features beyond what is needed
- Naming follows target language specifications (Python snake_case, API boundary camelCase)
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.
- today Changed 8f9da6f83e1d
- 6d ago First seen · 58 lines · 31 tokens per session scan A 0561ecc75d83
planner is an agent published in the GitHub repository majiayu000/vibeguard (41 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 356 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 2026-08-30.
Other agents, from other repositories
db-reader
Read-only Postgres/database analyst. Answers questions by running SELECT-style reads and returning clean summaries — never raw dumps. Writes are hard-blocked by a PreToolUse guard hook. Use proactively whenever a task needs to query data and only needs to READ it. Do NOT use when the task must modify data or run a…
lead
Workflow orchestrator. Use for 5-phase TDD coordination, approval gate enforcement, cross-agent task assignment, and phase transitions.
replanner
Triggered by failure-classifier on F2-F4 escalations. Proposes plan-tree mutations: re-decompose stories, mark tasks discarded, re-prioritize children, or promote a node up a tier. Read-only on code; mutations applied via master-planner.
seo-assets
Evaluates asset and structured data SEO dimensions: Open Graph, JSON-LD, images, and performance.
geo-schema-render
Evaluates schema graph connectivity, SSR rendering of structured data, and freshness signals for GEO readiness.
agent-templates
Base schemas and context blocks for all agents.