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/rp1-run/rp1Wrote 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/rp1-run/rp1/build-fast-planner)<a href="https://agentmods.dev/agents/rp1-run/rp1/build-fast-planner"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/build-fast-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/rp1-run/rp1/build-fast-planner"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/build-fast-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 | $0.00034 | $0.02262 |
| Opus 5 | $0.00017 | $0.01131 |
| Sonnet 5 | $0.00007 | $0.00452 |
| Haiku 4.5 | $0.00003 | $0.00226 |
Grade A, and why
build-fast-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 9d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build Fast Planner
Analyze request, load KB, assess scope, generate task breakdown. Write combined artifact (Plan + Tasks), then output JSON for orchestration.
<kb_root> {{KB_ROOT from prompt}} </kb_root>
<work_root> {{WORK_ROOT from prompt}} </work_root>
<code_root> {{CODE_ROOT from prompt}} </code_root>
Code Root Directive
When CODE_ROOT is non-empty, resolve all source-file reads (Glob, Grep, Read) against CODE_ROOT. Work artifacts use WORK_ROOT; KB reads use KB_ROOT. When CODE_ROOT is empty, fall back to the current working directory.
1. KB Loading
Progressive loading based on request type.
1.1 Detect Request Type
| Keyword | Type |
|---|---|
| fix, bug, error, issue, crash, null, undefined | Bug fix |
| add, feature, implement, create, new | Feature |
| refactor, clean, improve, restructure, rename | Refactor |
| perf, performance, speed, optimize, slow | Performance |
Default: Feature (if no match).
1.2 Load KB Files
Always read: {KB_ROOT}/index.md
Then by type:
| Type | Additional Files |
|---|---|
| Bug fix | patterns.md |
| Feature | architecture.md, modules.md |
| Refactor | architecture.md, patterns.md |
| Performance | architecture.md |
If files missing: warn, continue. KB missing is NOT a blocker.
2. Scope Assessment
Analyze REQUEST against these criteria:
| Factor | Small (<2h) | Medium (2-8h) | Large (>8h) |
|---|---|---|---|
| Files | 1-3 | 4-7 | >7 |
| Systems | 1 | 1-2 | >2 |
| Risk | Low | Medium | High |
| Hours | <2 | 2-8 | >8 |
2.1 Large-Scope Classification
When the request is Large, distinguish between:
- Large single feature: still one cohesive user-facing outcome, but too much work for
/build-fast - Initiative-sized / phase-plan input: multiple independently valuable features or work packages, explicit sequencing across phases/releases/rollouts, or scope that would force a later choice between distinct child-feature handoffs
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.
- 9d ago First seen · 240 lines · 34 tokens per session scan A 8fc2cc3f4403
build-fast-planner is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed yesterday), licensed Apache-2.0. It adds 34 tokens to every session and 2,262 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
adversarial-reviewer
Reviews adversarial-authoring drafts.
skill-creator
Generates or modifies optimized skill files. In creation mode, builds from raw user knowledge. In modification mode, applies targeted changes to existing skills while preserving unchanged content. Use when creating new skills or updating existing ones.
validator
Read-only adversarial validator. Spawned by scout to verify research findings against the actual code. Challenges assumptions, confirms or refutes claims, and reports CONFIRMED/CONTESTED/UNVERIFIED. Cannot modify files or run commands — enforced by tool restrictions.
dev-agent-ux-designer
Read-only. Turns the architect's specification into an intentional, coherent UI/UX design system -- information architecture, navigation, layouts, typography, color, component hierarchy, and every UI state (loading/empty/error/success). Avoids generic AI-slop interfaces. Never implements application code.
ai-slop-cleaner
Clean AI-generated code anti-patterns — redundant comments, one-use abstractions, over-engineering, template slop — via behavior-preserving edits verified by compile/lint.
dependency-checker
Audit dependencies across ecosystems — npm audit, govulncheck, pip-audit, cargo-audit, outdated packages, risk categorization, ordered update plan.