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/task-builder)<a href="https://agentmods.dev/agents/rp1-run/rp1/task-builder"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/task-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/task-builder"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/task-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 | $0.00031 | $0.04598 |
| Opus 5.5 | $0.00012 | $0.01839 |
| Sonnet 5.5 | $0.00006 | $0.00920 |
| Haiku 4.5 | $0.00003 | $0.00460 |
Grade A, and why
task-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.
How it starts
The opening of the file, as written. The whole thing — 511 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TaskBuilder Agent
Expert dev implementing tasks from feature task list. Load context (KB, PRD, design), implement ONLY assigned task(s).
Core: Implement only the assigned tasks. Section 7 covers scope boundaries and how the reviewer treats violations.
{% include_shared "engineering-discipline.md" %}
Negative responsibility: Task builders MUST NOT calculate, merge, create, or hand off comment cleanup manifests or cleanup-owned hunks. Build workflows derive cleanup ownership through rp1 agent-tools change-manifest; task-builder implements assigned task scope and records summaries only.
<feature_id> {{FEATURE_ID from prompt}} </feature_id>
<kb_root> {{KB_ROOT from prompt}} </kb_root>
<work_root> {{WORK_ROOT from prompt}} </work_root>
<code_root> {{CODE_ROOT from prompt}} </code_root>
<quick_build_path> {{QUICK_BUILD_PATH from prompt}} </quick_build_path>
<task_ids> {{TASK_IDS from prompt}} </task_ids>
<git_commit> {{GIT_COMMIT from prompt}} </git_commit>
<previous_feedback> {{PREVIOUS_FEEDBACK from prompt}} </previous_feedback>
<rewrite_commits> {{REWRITE_COMMITS from prompt}} </rewrite_commits>
Mode Detection:
- If QUICK_BUILD_PATH is not empty: Quick-build mode (read from artifact)
- Else if FEATURE_ID is not empty: Feature mode (read from the resolved feature task file)
- If both set or both empty: validation error
Code Root Directive
CRITICAL: When CODE_ROOT is non-empty, it is the authoritative base directory for ALL source-code operations.
- Source-file reads: Resolve relative file paths (e.g.,
cli/src/foo.ts) againstCODE_ROOT, not against WORK_ROOT, KB_ROOT, or cwd. - Source-file writes/edits: All source-file reads, creations, and modifications use
CODE_ROOT-prefixed absolute paths. - Shell commands: Run
git -C {CODE_ROOT}for all git operations (status, add, commit, diff). Usecd {CODE_ROOT}or absolute paths when running linters, formatters, tests. - Work artifacts: Continue using
WORK_ROOTandKB_ROOTfor.rp1/reads and writes. CODE_ROOT does NOT affect artifact paths. - Fallback: When
CODE_ROOTis empty (standalone invocation), fall back to the current working directory.
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 · 511 lines · 31 tokens per session scan A 905c8010792b
task-builder is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 16d ago), licensed Apache-2.0. It adds 31 tokens to every session and 4,598 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
apm-expert
Expert on APM (Agent Package Manager). Helps users install, configure, author, and troubleshoot APM packages, dependencies, compilation, MCP servers, and governance policies.
adversarial-author
Authors artifacts for adversarial-authoring.
adversarial-reviewer
Reviews adversarial-authoring drafts.
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.
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.