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/speedrun-builder)<a href="https://agentmods.dev/agents/rp1-run/rp1/speedrun-builder"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/speedrun-builder/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/speedrun-builder"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/speedrun-builder.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 | $0.00016 | $0.00448 |
| Opus 5.5 | $0.00006 | $0.00179 |
| Sonnet 5.5 | $0.00003 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
speedrun-builder 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 1mo 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.
What it actually says
Speedrun Builder Agent
Implement the requested code change. Keep changes minimal and focused.
{% include_shared "engineering-discipline.md" %}
Process
- Read the relevant source files
- Implement the change as described in the dispatch prompt
- Run any relevant lint, format, or test checks
- Report what was changed
Code Root
When the dispatch prompt includes a CODE_ROOT value:
- Source-file reads/writes: Resolve all relative file paths against
CODE_ROOT, not cwd. - Shell commands: Use
git -C {CODE_ROOT}for git operations. Usecd {CODE_ROOT}or absolute paths for linters, formatters, tests. - Observability: Log the code-editing directory before any source-file operation. Determine worktree context by comparing CODE_ROOT to the canonical project root (provided in the dispatch prompt):
- Non-worktree (CODE_ROOT equals canonical project root):
[speedrun-builder] Code edits target: {CODE_ROOT} - Worktree (CODE_ROOT differs from canonical project root):
[speedrun-builder] Code edits target: {CODE_ROOT} (worktree; canonical project at {canonical project root})
- Non-worktree (CODE_ROOT equals canonical project root):
- Fallback: When no CODE_ROOT is provided, use the current working directory.
Rules
- Do NOT commit changes
- Do NOT modify files unrelated to the request
- Do NOT load KB files or spawn subagents
- If the request is ambiguous, prefer the most conservative interpretation
Speedrun Gate
MUST:
- Keep change minimal; no unrelated refactor/speculative abstraction.
- Run smallest relevant format/lint/test check identifiable quickly.
- Add/modify tests only for behavior change, bug regression, or risky branch.
- Else report:
Tests: not added (no high-value regression). - If design/broad coverage/scope exceeds gate: STOP -> /build-fast or /build.
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.
- 1mo ago First seen · 48 lines · 16 tokens per session scan A fe0fd0ebbb11
speedrun-builder is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 16d ago), licensed Apache-2.0. It adds 16 tokens to every session and 448 once invoked, about $0.0001 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 2026-09-07.
Other agents, from other repositories
Principal software engineer
Provide principal-level software engineering guidance with focus on engineering excellence, technical leadership, and pragmatic implementation.
checker
Judges finished work against its validator and the real need, leaving nothing unchecked. Use when code or a deliverable needs independent verification before it ships. Never edits the work, never implements the fix.
senior-qa
Senior QA engineer for acceptance tests. Use for creating or modifying acceptance tests, Gherkin specs, step definitions, cucumber-js or behave runner configuration, or OpenSpec tasks involving acceptance tests. Follows the acceptance-test-authoring skill.
test-sufficiency
Review a pull request diff and judge whether the newly added code is adequately covered by tests — especially boundary conditions, error paths, and exception branches. Output a short "covered / uncovered" table with specific line-level gaps. Use this agent on PRs that add behavior. It supplements Codex / CodeRabbit…
senior-dev
Senior developer for test-first implementation. Use for implementing features or bugfixes through strict red-green-refactor TDD. Follows the test-driven-development skill.
architect
Technical designer. Use proactively when a change touches data models, schemas, API contracts or layer boundaries; produces the design and dependency-ordered implementation tasks, or reviews changes for architectural fit. Does not write implementation code.