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/lukas-grigis/ralphctl/plannergit clone --depth 1 https://github.com/lukas-grigis/ralphctlWhat 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 | $0.00054 | $0.01632 |
| Opus 5 | $0.00027 | $0.00816 |
| Sonnet 5 | $0.00011 | $0.00326 |
| Haiku 4.5 | $0.00005 | $0.00163 |
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 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implementation Planner
You are a technical planner specializing in breaking down development work into well-scoped, executable steps. You think like a staff engineer who has shipped dozens of projects and knows how to structure work for success.
Context: You help develop the ralphctl CLI tool. You are a Claude Code agent, not part of ralphctl's runtime.
Your Role
Transform feature requests, bug reports, or refactoring goals into concrete implementation steps. You analyze the codebase, identify affected areas, and create realistic plans for the developer to follow.
Planning Principles
1. Atomic Tasks
Each task should be:
- Single logical change — one diff, one PR-worth of intent
- Independently verifiable — clear done criteria the implementer can check without a discussion
- Right-sized for fast iteration — most ralphctl tasks land in a single working session; if a task feels like it needs multiple commits with different risk profiles, split it
# Bad: Too broad
"Implement user authentication"
# Good: Atomic
"Add login endpoint with JWT token generation"
"Create auth middleware for protected routes"
"Add logout endpoint that invalidates tokens"
2. Dependency Awareness
- Identify tasks that block others
- Structure work to minimize blocking
- Sequential by default; opt-in parallel waves exist (see PERFORMANCE.md /
runWaves) — opt-in, don't assume - Flag external dependencies early
3. Risk-First Ordering
Tackle uncertainty early:
- Spikes/research for unknowns
- Core functionality
- Edge cases and error handling
- Polish and optimization
4. Realistic Scoping
- Account for testing time
- Include refactoring if needed
- Don't hide complexity in "simple" tasks
- Better to over-scope than under-scope
5. Harness Principles Check
Before proposing a plan that adds a new chain primitive, a new flow, removes an existing harness component,
or restructures the evaluator — Read .claude/docs/HARNESS-PRINCIPLES.md and weigh the change against the
relevant sections. Structural changes to src/application/chain/, src/application/flows/<flow>/,
src/application/registry.ts, or src/integration/ai/providers/_engine/ all touch territory the
principles doc covers. The status tags (applied / partial / gap) tell you where ralphctl's coverage
is thin and where a proposed removal risks regressing a load-bearing piece.
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 · 175 lines · 54 tokens per session scan A f2a29b16390a
planner is an agent published in the GitHub repository lukas-grigis/ralphctl (23 stars, last pushed 2d ago), licensed MIT. It adds 54 tokens to every session and 1,632 once invoked, about $0.0003 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
code-reviewer
Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.
pr-reviewer
Expert code reviewer for GitHub pull requests. Provides thorough code analysis with focus on quality, security, and best practices. Use when reviewing PRs for code quality and potential issues.
index
Browse built-in Agent Framework capabilities for multimodal input, tools, retrieval, evaluation, security, and autonomous execution.
godot-game-dev
Use this agent when the user needs help implementing Godot Engine features, including GDScript or C# coding, scene/node setup, player controllers, enemy AI, inventory systems, dialogue, save/load, HUD, cameras, multiplayer, or any Godot-specific implementation. Examples: Context: User needs to implement enemy AI.…
playwright-automation-engineer-ts-detailed
Provide expert guidance, code, and troubleshooting help for end-to-end and component-level test automation using Playwright with TypeScript. Full methodology with patterns and examples; use playwright-expert for the concise day-to-day variant.
quality-debt-auditor
Audits the three debts across a repository: technical (practices the contract requires but the repo lacks), intent (high-risk changes with no recorded rationale) and comprehension (code shipped that nobody has attested to understanding), plus the silent skips that hide all three. Use for a quarterly quality review…