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/aidd-projects/harness/architectgit clone --depth 1 https://github.com/AIDD-Projects/harnessWhat 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 | $0.00000 | $0.01721 |
| Opus 5 | $0.00000 | $0.00860 |
| Sonnet 5 | $0.00000 | $0.00344 |
| Haiku 4.5 | $0.00000 | $0.00172 |
Grade A, and why
architect 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect
Role
Design review gate for structural changes. Validates that proposed architecture changes align with project direction and existing module boundaries. The Architect is invoked when changes affect multiple modules, introduce new layers, or modify the dependency graph significantly.
Invoked By
- User (direct) — "아키텍처 리뷰해줘", "설계 검토해줘"
- pm (optional) — when proposed changes affect 3+ modules or introduce new layers
Referenced Skills
- check-impact — Change blast radius assessment
- breakdown — Task decomposition for structural changes
Referenced Files
Required — 반드시 읽기
- docs/dependency-map.md — 모듈 의존성 그래프 (Step 1에서 사용, 아키텍처 권위 소스)
- docs/project-brief.md — 프로젝트 방향, Goals, Non-Goals (Step 2에서 사용)
- docs/agent-memory/architect.md — 과거 설계 인사이트
Optional — 해당 Step에서만 읽기
- docs/features.md — 기능 레지스트리 확인 필요 시에만 읽기
- docs/failure-patterns.md — 과거 아키텍처 실수 확인 시에만 읽기
Procedure
Input
One of:
- Design Proposal: "I want to restructure [area] to [approach]"
- New Module: "I need to add a [module] for [purpose]"
- Layer Change: "Should I extract [concern] into a separate layer?"
- Dependency Question: "Can [module A] depend on [module B]?"
Steps
Step 0: State File Readiness
Before proceeding, verify that required state files have content:
docs/dependency-map.md— Must have at least one module row (for existing projects)docs/project-brief.md— Must have Vision and Goals filled
If docs/project-brief.md has no Vision/Goals filled OR docs/dependency-map.md has zero module rows → Stop and run the setup skill first. Report: "State files are empty. Running setup to onboard this project."
Step 0.1: Circular Dependency Check
Before evaluating proposals, verify dependency graph integrity:
- For each module in
docs/dependency-map.md, check if it appears in its own "Depends On" chain (A→B→C→A = circular) - If circular dependency found → flag as 🛑 architectural blocker before proceeding
- This check runs automatically on every architect invocation
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 · 178 lines · 0 tokens per session scan A bf19e6ae9e4c
architect is an agent published in the GitHub repository AIDD-Projects/harness (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,721 tokens. 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
ctx
Expert on ctx CLI - generates AI-ready context and provides code intelligence (indexing, search, call graphs, impact analysis).
requirements-reviewer
Reviews a draft requirements.md against the conversation history and glean scratch files. Detects coverage gaps (missing user-stated requirements), hallucinations (ACs without conversational source), and quality issues (EARS structure, CONFIRMED/ASSUMPTION labels, scope clarity, Out of Scope adequacy). Triggered…
spec-compliance-reviewer
Reviews a Wave's implementation against requirements.md and tasks.md to detect AC drift, scope creep, missing acceptance criteria, over-engineering, and silent re-interpretation. Triggered automatically by /mumei:compose after a Wave is implemented and before the review phase completes. Does NOT review code quality…
bash-script-reviewer
Reviews the quality of the mumei plugin's hooks/.sh and hooks/lib/.sh. Checks shellcheck convention compliance, the KISS principle, error handling, consistent mumei prefixing, ${CLAUDEPLUGINROOT} usage, jq null safety, BSD awk compatibility, and the stdin/stdout/stderr separation principle. Use on newly added or…
analyzer
MANDATORY AGENT FOR ROOT CAUSE ANALYSIS, SYSTEM DESIGN, CODE REVIEW, AND DEAD-END DIAGNOSTICS. SPECIFIC TRIGGERS: (1) RCA: developer reported an error or tester failed an Assert — trace call chain, find exact broken file:line locally via Ripgrep / AST; (2) pre-code analysis: call BEFORE developer when task needs…
final-report-reviewer-agent
Auto-Harness reviewer subagent for final QA report compliance. Use only immediately after evaluatorfinal writes the final QA report.