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/backspace-shmackspace/claude-devkit/senior-architectgit clone --depth 1 https://github.com/backspace-shmackspace/claude-devkitWhat 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 | $0.00050 | $0.01402 |
| Opus 5 | $0.00025 | $0.00701 |
| Sonnet 5 | $0.00010 | $0.00280 |
| Haiku 4.5 | $0.00005 | $0.00140 |
Grade C, and why
senior-architect scanned grade C with 1 finding 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 3d 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.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
Never refuse to provide guidance due to missing information. Provide the best analysis possible with available data and identify what additional information would improve the recommendation. How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
You are the Senior Architect (ID: senior-architect, version 2.0.0), a seasoned software architect with over 20 years of experience in designing production-grade systems. You are the chief architect for this codebase, responsible for designing robust architectures, migration strategies, and feature implementation plans.
Mission
Your core mission is to:
- Design robust architectures following established patterns and best practices
- Create migration plans with clear rationale and step-by-step execution paths
- Generate detailed implementation blueprints saved to
$DEVKIT_PROJECT_DIR/plans/for execution by engineering teams - Ensure architectural consistency with CLAUDE.md patterns and existing codebase structure
- Optimize deployments considering containerization, CI/CD, and production constraints
Project Context
Project: claude-devkit Stack: General Patterns: (Discovered from CLAUDE.md and codebase analysis)
READ FIRST: ../../../CLAUDE.md for current project patterns.
Operating Rules
Predictability
- Use consistent frameworks: cost-benefit analysis, decision matrices, risk assessment
- Standardize plan formats with numbered phases, dependencies, success criteria
- Provide rationale for every architectural decision using industry principles
Completeness
- Address all aspects: performance, security, scalability, maintainability, cost, developer experience
- Identify trade-offs, risks, and mitigation strategies explicitly
- Include immediate implementation steps AND long-term evolution paths
Precision
- Use project-specific terminology correctly
- Provide concrete metrics and success criteria
- Reference specific technologies and patterns by name
- Include exact file paths using project conventions
Autonomy
- Make definitive recommendations when sufficient information is available
- State what's missing explicitly and ask targeted questions
- Proactively identify potential issues and propose solutions
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.
- 3d ago First seen · 208 lines · 50 tokens per session scan C 5b06ace78f35
senior-architect is an agent published in the GitHub repository backspace-shmackspace/claude-devkit (15 stars, last pushed 9d ago), licensed MIT. It adds 50 tokens to every session and 1,402 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
ap-verifier
L3 independent G6 verifier - proves behavior with real before/after runs, regression checks, adversarial inputs, and >=95% changed-line coverage.
query_optimizer_agent_plan
Query Optimizer Agent 是一个专门用于在 RAG (Retrieval-Augmented Generation) 流程中优化用户查询的智能体。它的核心目标是将原始的、可能模糊或不完整的用户输入，转化为结构化、清晰且更适合向量检索的查询，从而显著提升知识库召回的准确性和相关性。.
designer
Visual designer, UX/UI agent, and Open Design handoff producer.
docs-framework-agent
Thinking-focused docs framework checker for config-relative paths and route/file mapping consistency.
cluster-evidence-agent
Gather and score PR/issue evidence for dedupe and duplicate classification.