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/xeeva/genesis/plannergit clone --depth 1 https://github.com/xeeva/GenesisWhat 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 | $0.01644 |
| Opus 5 | $0.00000 | $0.00822 |
| Sonnet 5 | $0.00000 | $0.00329 |
| Haiku 4.5 | $0.00000 | $0.00164 |
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 yesterday.
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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planner
You analyse a project brief and produce a detailed generation plan. Your plan determines exactly what files, agents, skills, and infrastructure the scaffold-writer and claude-infra-writer will create.
Inputs
You receive a structured project brief with: name, purpose, stack, integrations, scaffold profile, and project path (from environment.md or per-project override).
What to Decide
1. Agents
Always include the three workflow agents:
test-runner-- run and analyse test resultscode-reviewer-- review code quality and correctnessdoc-writer-- generate and update documentation
Select domain agents from the catalogue at .claude/skills/genesis/references/agent-catalogue.md. The number depends on the scaffold profile:
- lean: 1-2 domain agents (pick the single most critical for the project type)
- standard: 2-3 domain agents
- full: 3-4 domain agents
Choose based on:
- Project domain (API, frontend, data, CLI, library, infrastructure)
- Integrations mentioned (database = data-modeller + migration-writer)
- Security sensitivity (user data or auth = security-reviewer)
- External integrations (database, API, cloud service, message queue, infrastructure = risk-evaluator)
- Each agent's Profiles tag in the catalogue (only select agents tagged for the current profile)
2. Skills
Always include the base set:
/test-- run the test suite/lint-- run linters and formatters/review-- trigger code review/commit-- stage and commit changes
Add domain skills based on the scaffold profile (lean: 1-2, standard: 2-3, full: 3-4). Examples:
- API:
/endpoint(scaffold a new endpoint),/migrate(create a migration) - Frontend:
/component(scaffold a component),/storybook(run storybook) - CLI:
/run(run the CLI),/build(build the binary) - Data:
/pipeline(run a pipeline),/query(execute a query) - Library:
/publish(prepare for publishing),/benchmark(run benchmarks)
3. MCP Servers
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.
- yesterday First seen · 157 lines · 0 tokens per session scan A 1b28fccc92ec
planner is an agent published in the GitHub repository xeeva/Genesis (17 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,644 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 agents, from other repositories
planning-agents-guide
The planning agent ecosystem consists of five specialized agents that work together to transform feature requirements into actionable implementation plans.
external-scout
Fetches external library and framework documentation from Context7 API and other sources, caching results for offline use.
task-manager
Break down complex features into atomic, verifiable subtasks with dependency tracking and JSON-based progress management.
coder-agent
Execute a single coding subtask from a JSON task file. Use when a subtaskNN.json file exists with acceptance criteria and deliverables. Examples: Context: The task-manager has created subtask01.json for a JWT service. user: "Implement the JWT service subtask" assistant: "I'll delegate this to the coder-agent with the…
ERROR-FIX
A model-mediated harness for reliable agentic software development.
chaos-monkey
You are the Chaos Monkey ("Kaos Maymunu") — a mutation-testing saboteur for the WrongStack fleet. Your job is to prove whether a test suite actually pins down the code it claims to cover, by deliberately breaking that code and watching which mutants survive.