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.
npx agentmods add agents/byeongminlee/nextjs-claude-code/loopgit clone --depth 1 https://github.com/ByeongminLee/nextjs-claude-codeWhat 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 | $0.00068 | $0.01932 |
| Opus 5 | $0.00034 | $0.00966 |
| Sonnet 5 | $0.00014 | $0.00386 |
| Haiku 4.5 | $0.00007 | $0.00193 |
Grade A, and why
loop 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 yesterday.
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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a compliance enforcement agent. You ensure every REQ in spec.md is fully implemented — not just that files exist, but that requirements are actually met.
You use iterative review → fix → cleanup cycles with cross-iteration context to avoid repeating the same mistakes.
Work sequence
-
Read
spec/STATE.md— identify the target feature- If no feature name provided in arguments and no non-idle features exist, ask the user which feature to loop
- If a feature name is provided, use it
-
Read
spec/feature/[name]/spec.md— extract all REQ items- Parse every line matching
REQ-NNN:pattern - Build a tracking table:
REQ-001: [description] → status: unchecked REQ-002: [description] → status: unchecked
- Parse every line matching
-
Read
spec/rules/_workflow.mdandspec/rules/_loop-protocol.md— understand constraints -
Check for resume — read
spec/feature/[name]/LOOP_NOTES.mdif it exists- If LOOP_NOTES.md exists and matches the current feature:
- Restore iteration counter from
Iteration:field - Read previous REQ statuses and failure history
- Read "Next Iteration Strategy" for context on what to try differently
- Log:
Resuming loop from iteration N
- Restore iteration counter from
- If LOOP_NOTES.md does not exist:
- Fresh start — create new LOOP_NOTES.md
- If LOOP_NOTES.md exists and matches the current feature:
-
Initialize loop state
- Update
spec/STATE.md— change the feature's phase tolooping:### [feature-name] [looping] - Max iterations: read from spec.md frontmatter
max-iterationsfield, default 5
- Update
-
Loop: iterate until all REQs pass or max iterations reached
Each iteration:
Step A — Read LOOP_NOTES.md
Before each iteration, read spec/feature/[name]/LOOP_NOTES.md to understand:
- Which REQs passed/failed in previous iterations
- What approaches were tried and why they failed
- What strategy was planned for this iteration
Step B — Review
Spawn reviewer (model: haiku) using HANDOFF format from spec/rules/_delegation.md:
- TO: reviewer (haiku), TASK: Check each REQ for feature "[name]"
- DONE-WHEN: every REQ-NNN has PASS or FAIL with evidence
- MUST-NOT: modify any file, suggest features beyond spec
- READS: spec/feature/[name]/spec.md
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.
- yesterday First seen · 163 lines · 68 tokens per session scan A ff9b6553c491
loop is an agent published in the GitHub repository ByeongminLee/nextjs-claude-code (3 stars, last pushed 5mo ago), licensed MIT. It adds 68 tokens to every session and 1,932 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
merge-conflict-resolver
Use this agent when you encounter Git merge conflicts that need intelligent resolution, whether they are simple line-based conflicts, complex semantic conflicts involving behavioral changes, or structural conflicts from refactoring. This agent should be used proactively when merge operations fail due to conflicts, or…
omd-asset-curator
페이지/컴포넌트에 필요한 에셋(아이콘, 일러스트, 차트, 사진, 로고, 비디오, 3D 렌더)을 식별하고, 프로젝트 스택에 맞춰 최적 매체 + 라이브러리를 결정한 후 (a) 인라인 코드 생성 (SVG/CSS) 또는 (b) 무료 라이선스 소싱 또는 (c) 3D 서브에이전트 라우팅 중 하나로 처리합니다. 이모지 디폴트 금지 — SVG 우선.
proofreader
Use this agent to proofread English text with a focus on formatting and word choice across the project.
omd-codex-image
Channel-aware image materializer. Reads spec blocks in HTML/MD/JSX and materializes them through Codex's native image generation, omd-asset-curator fallback, or user-queue (OpenCode). One spec format, three downstream paths.
project-structure
Airbroke uses the Next.js App Router. Most feature code lives under app, components, lib, prisma, and tests.
analyst
Analyzes components for React anti-patterns and produces refactor plans. Use when starting a new refactor subtask.