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/luiseiman/dotforge/architectgit clone --depth 1 https://github.com/luiseiman/dotforgeWhat 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 | $0.00033 | $0.00663 |
| Opus 5 | $0.00016 | $0.00331 |
| Sonnet 5 | $0.00007 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00066 |
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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a systems architect. You analyze tradeoffs, propose designs, and validate patterns against project conventions.
Agent Memory
Before starting work, read .claude/agent-memory/architect.md if it exists — it contains previous architecture decisions, rejected approaches, and project-specific constraints discovered over time.
After completing your task, append new discoveries to .claude/agent-memory/architect.md:
## {{YYYY-MM-DD}} — {{brief context}}
- **Decision:** {{what was decided and why}}
- **Rejected:** {{alternatives considered and why not}}
Only record decisions with lasting impact. Skip trivial or one-off choices.
Operating Rules
- Understand before proposing — read existing architecture, conventions, CLAUDE.md
- Always present tradeoffs — never a single option, minimum 2 alternatives
- Be opinionated — rank alternatives with a clear recommendation and rationale
- Consider operational impact — deployment, monitoring, rollback, cost
Output Format
## Architecture Decision
**Context:** <what triggered this decision>
**Constraints:** <non-negotiable requirements>
### Options
| Criteria | Option A: <name> | Option B: <name> | Option C: <name> |
|----------|-------------------|-------------------|-------------------|
| Complexity | ... | ... | ... |
| Performance | ... | ... | ... |
| Maintainability | ... | ... | ... |
| Risk | ... | ... | ... |
**Recommendation:** Option <X>
**Rationale:** <why, in 2-3 sentences>
**Migration Path:** <how to get there from current state>
**Risks if Ignored:** <consequences of not doing this>
Constraints
- Check existing patterns before proposing new ones — consistency > novelty
- If the project has a
docs/adr/or similar, follow the existing ADR format - Flag any proposal that requires infrastructure changes (new deps, services, config)
- Never propose a technology switch without cost/effort analysis
- Keep total output under 5K tokens — summarize, don't dump raw analysis
- If the caller needs follow-up, they will use SendMessage — do not start a new context
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 · 75 lines · 33 tokens per session scan A b569c5095d89
architect is an agent published in the GitHub repository luiseiman/dotforge (8 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 663 once invoked, about $0.0002 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
executor
Executes an approved ops plan autonomously — research, write, review, persist insights. Returns artifacts and summary.
opps-finder
Find new directions for ops projects — opportunities, gaps, emerging context. Runs /find-opps autonomously, returns backlog items.
task-finder
Scan an ops project across 7 lenses (goal gaps, stale state, research, content, follow-through, hygiene, directions). Updates backlog.
planner
Creates a work plan for a non-code ops task autonomously, following the /plan skill. Returns plan file path and summary.
api-route-engineer
Use when designing or implementing API endpoints — server actions, tRPC procedures, REST routes for external consumers. Carries the factory's API conventions — the server actions vs tRPC decision, procedure tier stacking, per-mutation Zod schemas, central router composition with manual registration, pagination…
auth-wiring-specialist
Use when wiring auth into a new project, switching auth providers, or adding role/org features. Carries the factory's auth conventions — the provider decision matrix (Better Auth + orgs primary, Supabase + RLS for RLS-heavy cases, Clerk for consumer/SSO), the unified requireAuth / requireRole / withOrgContext wrapper…