build-artifact-detector

build-artifact-detector is an agent for Claude Code from rp1-run/rp1. It costs 22 tokens per session (1,075 once invoked), scanned A, original, Apache-2.0.

An agent that checks whether the documents and other files needed for a feature-building workflow already exist and are valid. It then identifies the first build step that needs work.

In plain words
What is it for?
Checking requirements, architecture, task lists, and pending tasks to decide where a feature workflow should begin or resume.
Why use it?
It prevents a workflow from restarting unnecessarily or continuing from incomplete requirements, design, or task files.

Agent for Claude Code

Written for Claude Code: arguments in frontmatter. Also seen: model in frontmatter; positional $N argument.

Part of the rp1-dev plugin — 23 skills, 36 agents shipped together

Good fit Checking requirements, architecture, task lists, and pending tasks to decide where a feature workflow should begin or resume.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rp1-run/rp1/build-artifact-detector
Install

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.

Clone the repo
git clone --depth 1 https://github.com/rp1-run/rp1

Made for: Claude Code.

Or install rp1-dev, the plugin that ships this one along with the rest of its 23 skills, 36 agents.

Wrote 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.

agentmods badge for build-artifact-detector

README.md
[![agentmods](https://agentmods.dev/badge/agents/rp1-run/rp1/build-artifact-detector/github.svg)](https://agentmods.dev/agents/rp1-run/rp1/build-artifact-detector)
Your own site
<a href="https://agentmods.dev/agents/rp1-run/rp1/build-artifact-detector"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/build-artifact-detector/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.

agentmods 80×15 button for build-artifact-detector

Your own site · 80×15
<a href="https://agentmods.dev/agents/rp1-run/rp1/build-artifact-detector"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/build-artifact-detector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,075 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.01075
Opus 5 $0.00011 $0.00537
Sonnet 5 $0.00004 $0.00215
Haiku 4.5 $0.00002 $0.00108

Measured 9d ago against content hash 78cc1c42e80d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

build-artifact-detector 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.

plugins/dev/agents/build-artifact-detector.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build Artifact Detector

Determines which build step to start from by checking artifact existence and validity. The parent tracked workflow already resolved run reuse through workflow bootstrap, so this agent only consumes the provided canonical run context.

CRITICAL: Output ONLY JSON. No explanations, no progress updates.

<feature_id>$1</feature_id> <workflow_type>$2</workflow_type> <run_id>$3</run_id> <run_resumed>$4</run_resumed> <work_root>$5</work_root>

1. Detection Algorithm

Check artifacts in order. First failing check determines start_step.

Step 1: Requirements

Read {WORK_ROOT}/features/{FEATURE_ID}/requirements.md

  • Valid if: Contains ## 5. Functional Requirements
  • Missing/invalid: start_step = 1, STOP

Step 2: Design

Read {WORK_ROOT}/features/{FEATURE_ID}/design.md

  • Valid if: Contains ## 2. Architecture
  • Missing/invalid: start_step = 2, STOP

Step 3: Tasks

Read {WORK_ROOT}/features/{FEATURE_ID}/tasks.md

  • Valid if: Contains task entries (- [ ] or - [x])
  • Missing/no entries: start_step = 3, STOP

Step 4: Tasks Pending

Check tasks.md for pending tasks.

  • Pending if: Contains - [ ] (unchecked tasks)
  • Has pending: start_step = 4, STOP

Step 5: Verification

Glob {WORK_ROOT}/features/{FEATURE_ID}/feature_verify_report*.md, read most recent.

  • Verified if: Contains BOTH Overall Status: VERIFIED AND Ready for Merge: YES
  • Not verified: start_step = 5, STOP

Step 6: Archive

All checks passed: start_step = 6

2. Run Context

Use the bootstrap-provided run context directly:

  • run_id = {RUN_ID}
  • resumed = {RUN_RESUMED}

Do NOT extract rp1_run_id frontmatter and do NOT call rp1 agent-tools emit resume-run.

2.1 Artifact Reconciliation (Best-Effort)

When resumed is true, scan the feature directory {WORK_ROOT}/features/{FEATURE_ID}/ for .md files that may not be registered under the resumed run. Report these as unregistered_artifacts using work-root-relative paths so the calling skill can register them directly.

Read the full file on GitHub · 130 lines

Changes

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.

  1. 9d ago First seen · 130 lines · 22 tokens per session scan A 78cc1c42e80d

Subscribe to this mod's changes

build-artifact-detector is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 2d ago), licensed Apache-2.0. It adds 22 tokens to every session and 1,075 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

adversarial-reviewer

Reviews adversarial-authoring drafts.

intent-driven-dev/intent-driven-template · 7 tokens

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.

shinpr/rashomon · 47 tokens

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.

justinjdev/fellowship · 56 tokens

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.

Surjal/dev-agent · 58 tokens

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.

RaNDoM6913/claude-code-superkit · 40 tokens

behavioral-nudge-engine

Behavioral psychology specialist for retention, habit loops, and notification cadence. Designs nudges that increase user engagement without burning them out. Use when building reminders, streak mechanics, onboarding sequences, or social-app retention features.

RaNDoM6913/claude-code-superkit · 48 tokens