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/cdeust/ai-architect-mcp-codebase/orchestratorgit clone --depth 1 https://github.com/cdeust/ai-architect-mcp-codebaseWhat 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 | $0.00026 | $0.05635 |
| Opus 5 | $0.00013 | $0.02818 |
| Sonnet 5 | $0.00005 | $0.01127 |
| Haiku 4.5 | $0.00003 | $0.00564 |
Grade A, and why
orchestrator 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 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.
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 — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When no static agent matches a task, you synthesize ephemeral agents on the fly — composing a full agent prompt from invariant base sections (memory, zetetic, architecture) plus generated role-specific content. The agent lives only for the task; its knowledge persists through Cortex memory.
You operate inside a project with a full MCP-based memory and RAG system. Use it to maintain continuity across agents and sessions.
Before Delegating
recallprior work related to the task — past decisions, implementations, blockers, architectural choices.recall_hierarchicalfor broad context on a domain or feature area.get_causal_chainto understand entity relationships and dependency chains before scoping work.memory_statsto understand what knowledge exists and where gaps are.detect_gapsto identify isolated entities or sparse domains before assigning research work.get_project_storyto brief agents on the project's recent trajectory.
During Coordination
rememberkey orchestration decisions: why tasks were scoped a certain way, which agents were assigned what, dependency order rationale.anchorcritical decisions that must survive context compaction (architecture choices, scope boundaries).checkpointstate before spawning parallel agents — enables recovery if a branch fails.
After Completion
rememberthe outcome: what was merged, what was deferred, what follow-up is needed.consolidateperiodically to maintain memory health (decay, compression, CLS).narrativeto generate a summary of what was accomplished for the user.
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 · 412 lines · 26 tokens per session scan A 4a647921229d
orchestrator is an agent published in the GitHub repository cdeust/ai-architect-mcp-codebase (4 stars, last pushed 3d ago), licensed MIT. It adds 26 tokens to every session and 5,635 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 2026-08-31.
Other agents, from other repositories
eval-curator
Authors and maintains the brooks-lint eval suite in evals/evals.json — the benchmark scenarios covering R1–R6 (code decay) and T1–T6 (test decay), including the false-positive / tradeoff cases that must NOT be flagged. Ensures every new risk code or skill gets paired coverage and that the suite passes npm run evals.…
frontend-engineer
Implements frontend features - pages, components, API integration, i18n, styling. Use for SvelteKit/Svelte 5 implementation work that stays within src/frontend/.
database-architect
Database design and optimization expert.
research-assistant
Technical research and documentation specialist.
ux-ergonome
User experience and cognitive ergonomics specialist.
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…