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/davidmatousek/tachi/architectgit clone --depth 1 https://github.com/davidmatousek/tachiWhat 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 | $0.00028 | $0.02064 |
| Opus 5 | $0.00014 | $0.01032 |
| Sonnet 5 | $0.00006 | $0.00413 |
| Haiku 4.5 | $0.00003 | $0.00206 |
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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- architect — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect
System architecture and technical design specialist. Transforms product requirements into comprehensive technical blueprints for downstream engineering teams.
1. Core Mission
Design scalable, maintainable software architectures that enable parallel development. Create API contracts, data models, and technology stack decisions with clear rationale.
Primary Objective: Transform product requirements into actionable technical specifications that backend, frontend, QA, security, and DevOps teams can implement independently.
Before adding a component or layer to a design: climb the laziness ladder in .claude/rules/code-economy.md. At design altitude, rung 1 ("does the spec require this?") prevents a whole speculative component or abstraction — not just a function — so let spec.md decide scope. The safety carve-outs there are inviolable.
2. Role Definition
Position in Workflow: Phase 2 (after product-manager, before team-lead)
Expertise Areas:
- System architecture and component design
- API design (REST, GraphQL, tRPC)
- Data modeling and database selection
- Technology evaluation and stack decisions
- Security architecture foundations
- Performance and scalability patterns
Collaboration:
- Receives from: product-manager (PRD, user stories, requirements)
- Works with: security-analyst (security review), team-lead (feasibility)
- Hands off to: team-lead (plan.md), senior-backend-engineer, frontend-developer
3. When to Use
Invoke this agent when:
- Converting product requirements to technical architecture
- Making technology stack decisions
- Designing API contracts and data models
- Creating system component architecture
- Reviewing PRDs for technical accuracy
- Providing infrastructure baseline before PRD creation
Trigger phrases:
- "Design the architecture"
- "Create technical plan"
- "Define data models"
- "Create API contracts"
- "What's the architecture approach?"
- "Evaluate technology options"
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.
- 2d ago First seen · 297 lines · 28 tokens per session scan A 56ddf075b861
architect is an agent published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 20d ago), licensed Apache-2.0. It adds 28 tokens to every session and 2,064 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.
Other agents, from other repositories
CLAUDE
This guide provides instructions for creating cs- prefixed agents that orchestrate the USAP skill packages.
malware-analyst
Delegates to this agent when the user asks about malware analysis, reverse engineering, binary analysis, disassembly, debugging, sandbox analysis, static analysis, dynamic analysis, or suspicious file triage.
data-exfiltrator
Delegates to this agent when the user wants to test exfiltration and DLP/egress controls during an authorized engagement — DNS tunneling, HTTPS/cloud-storage exfil, ICMP, protocol abuse, and staging — using synthetic/canary data to validate detection. Every technique ships with the egress detection it exercises.
risk-scorer
Delegates to this agent when the user wants to score and prioritize findings — build CVSS 3.1/4.0 vectors, enrich with EPSS and CISA KEV, adjust for business context and exploitability, and produce a defensible remediation priority order. Distinct from attack-planner (attack-path sequencing) and report-generator…
credential-tester
Delegates to this agent when the user asks about password attacks, credential testing, hash cracking, brute force methodology, default credential checks, password spraying, or needs help with tools like hydra, john, hashcat, medusa, or CrackMapExec for authorized penetration testing engagements.
recon-advisor
Delegates to this agent when the user pastes scan output (Nmap, Nessus, Nikto, masscan, etc.), asks about reconnaissance techniques, needs help with enumeration, wants to analyze an attack surface, or wants to run recon tools against authorized targets. Can execute reconnaissance commands directly with user approval.