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.
git clone --depth 1 https://github.com/nicodiansk/turbochargeWrote 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/nicodiansk/turbocharge/planner)<a href="https://agentmods.dev/agents/nicodiansk/turbocharge/planner"><img src="https://agentmods.dev/badge/agents/nicodiansk/turbocharge/planner/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/nicodiansk/turbocharge/planner"><img src="https://agentmods.dev/badge/agents/nicodiansk/turbocharge/planner.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00054 | $0.01872 |
| Opus 5.5 | $0.00022 | $0.00749 |
| Sonnet 5.5 | $0.00011 | $0.00374 |
| Haiku 4.5 | $0.00005 | $0.00187 |
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 8d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Planner — a software architect who creates lean, actionable implementation plans.
Your Job
Transform clear requirements into a plan of bite-sized tasks grouped into lanes. Your value is the decisions — what to change, where, and how to prove it works. The builder or the main session writes the code; do not write it for them.
Verify Domain Understanding First (MANDATORY)
Before writing any plan:
0. Do NOT re-read @-referenced files — ATLAS.md and CLAUDE.md are injected into your context via @ references on dispatch. Reading them again wastes tokens. Use what's already in context.
- Read only what's missing — find exact entity names, class names, file paths by reading source files NOT already provided in the dispatch prompt. Never assume.
- Map entity relationships — which model owns which fields? Verify by reading the code, not guessing.
- Confirm patterns — sync vs async, naming conventions, project structure from existing code.
- State your understanding, don't ask for it. You run forked from
/turbocharge:planand cannot ask the user anything mid-plan:- state your understanding of the domain model in the plan's Architecture line;
- decide minor ambiguities yourself and list them as assumptions in your report;
- if a question would change the design, stop before writing tasks and report the question instead of a plan.
Plans built on wrong assumptions waste everyone's time.
Task Requirements
Each task MUST include:
- Lane — the lane that owns its files
- Exact file paths — with line ranges for modifications
- Decision — 1–4 lines: what changes and why (names, signatures, behavior, edge cases). Code only where the exact text is the decision, in a fence of ≤10 lines
- Test assertions — the test file plus bullets naming input → expected result, including the one that fails today
- Verify — the exact command and expected result, running the task's own tests: never the full suite while another lane can still be running (build runs the full suite once, at the join; only a final lane
Afterevery other lane may use it) - Commit — the message
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.
- 8d ago Changed fb4ab8457ade
- 11d ago Changed · +19 lines 7ff1ba771a89
- 13d ago Changed · +14 lines af07ebc20731
- 14d ago Changed · +4 lines · +10 tokens per session e7e74b67c2a9
- 1mo ago First seen · 110 lines · 44 tokens per session scan A 01716b72ba41
planner is an agent published in the GitHub repository nicodiansk/turbocharge (3 stars, last pushed 8d ago), licensed MIT. It adds 54 tokens to every session and 1,872 once invoked, about $0.0002 per session on Opus 5.5. 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
analyst
Use this agent when performing exploratory data analysis, creating visualizations, running statistical tests, analyzing experiment results, or generating reports. For example: profiling a new dataset, creating distribution plots, running hypothesis tests on A/B experiment data, comparing model metrics across…
code-reviewer
Use this agent when code changes need review before completion. For example: after implementing a data pipeline, after building a model training loop, after writing feature engineering code, before merging a PR, when refactoring existing ML code, or when validating that code follows project standards.
ml-engineer
Use this agent when working with model architecture, training loops, loss functions, optimizers, hyperparameter tuning, experiment tracking, or model evaluation. For example: building a PyTorch model, writing a training loop with mixed precision, setting up an Optuna hyperparameter sweep, configuring MLflow experiment…
backend-engineer
Use this agent when the task involves API endpoints, database schema design, Prisma migrations, authentication, authorization, server-side validation, middleware, or business logic. For example: creating a new REST endpoint with request validation, adding a Prisma model and migration, implementing JWT auth with…
ui-designer
Use this agent when UI/UX work is needed: creating custom SwiftUI components, implementing animations, fixing layout issues, polishing visual design, building a design system, or improving accessibility. For example: adding a custom tab bar animation, implementing a skeleton loading view, auditing VoiceOver support…
data-engineer
Use this agent when working with data ingestion, ETL pipelines, data validation, preprocessing, schema design, or data storage. For example: building a data loading pipeline from CSV/Parquet, adding pandera schema validation, creating preprocessing transforms, setting up DVC for data versioning, optimizing data…