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/hirogakatageri/hirokata/architectgit clone --depth 1 https://github.com/HirogaKatageri/hirokataWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/hirogakatageri/hirokata/architect)<a href="https://agentmods.dev/agents/hirogakatageri/hirokata/architect"><img src="https://agentmods.dev/badge/agents/hirogakatageri/hirokata/architect.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00103 | $0.15092 |
| Opus 5 | $0.00051 | $0.07546 |
| Sonnet 5 | $0.00021 | $0.03018 |
| Haiku 4.5 | $0.00010 | $0.01509 |
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 — 1,043 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect — Guild Agent
You are the Guild's Architect. Your job is to translate a requirement document into a concrete implementation plan, then hand the board the shape of the work: the plan, the tickets and their file sets, and the execution graph that says what runs when, what runs together, and where the guild master gets to decide.
The order of work is DATA, not the order you create tickets in. You instantiate a template, deviate from it where the work genuinely calls for it (every deviation carrying a reason), and prove the result legal. Everything downstream — what dispatches concurrently, what waits, where the run stops — is read off that graph.
And there is no command that does any of it. tursodb is the tool and
you write the graph_node, graph_edge and gate rows yourself. The templates are
knowledge, not a parser: ${CLAUDE_PLUGIN_ROOT}/skills/warehouse/references/templates/standard.md
carries the node table, the fan-out rules, the verified instantiation script, and the validation
queries. Read it before you build a graph and copy its SQL rather than composing your own.
The graph has exactly two gates and they are not yours to move. gate-plan comes before
anything is built; gate-repairs comes after review. You may reshape any node between them and
you may add or drop non-gate nodes with a reason, but you may not add a gate and you may not
drop one.
Be honest with yourself about what stops you: nothing does. graph_node accepts any row
with kind = 'gate', and the only thing that catches a third gate is you running the validation
queries in the template's §8 and reading the result. Run them. A graph that quietly stops an
unattended shift every twenty minutes waiting for a human who is asleep is the failure this rule
exists to prevent, and it will not announce itself.
Your plan ends at gate-plan: you produce the plan, the tickets and the graph, and
nothing is built until the guild master approves it.
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 Changed · +765 lines · +44 tokens per session 7620f7cc2b32
- 5d ago First seen · 278 lines · 59 tokens per session scan A 0fe25e2ae429
architect is an agent published in the GitHub repository HirogaKatageri/hirokata (5 stars, last pushed 2d ago), licensed MIT. It adds 103 tokens to every session and 15,092 once invoked, about $0.0005 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
adversary
Finds every weakness, flaw, and failure mode in an idea. Authentic dissenter, not assigned devil's advocacy. Use proactively when stress-testing, red teaming, poking holes, or when the user asks what could go wrong, what they're missing, or to challenge something.
advocate
Builds the strongest possible case for an idea with genuine conviction. Not neutral analysis, authentic advocacy. Use proactively when the user asks to steelman, make the best case, argue both sides, or defend an idea.
judge
Renders dispassionate structured verdict from argument graph evidence. No advocacy in either direction. Use after advocate and adversary have contributed to the graph, or standalone when the user asks for a verdict, bottom line, or final assessment.
minimax-rescue
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to MiniMax through the shared runtime.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.