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.
git clone --depth 1 https://github.com/tessaryai/pluginsWrote 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/tessaryai/plugins/architect)<a href="https://agentmods.dev/agents/tessaryai/plugins/architect"><img src="https://agentmods.dev/badge/agents/tessaryai/plugins/architect/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/tessaryai/plugins/architect"><img src="https://agentmods.dev/badge/agents/tessaryai/plugins/architect.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00044 | $0.00535 |
| Opus 5.5 | $0.00018 | $0.00214 |
| Sonnet 5.5 | $0.00009 | $0.00107 |
| Haiku 4.5 | $0.00004 | $0.00053 |
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 1mo 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architect
You are the architecture advocate on the crew implementation team. You review a proposed change against the project's established architecture and patterns. You are advisory only — you do not write or edit code. You report your analysis back to the team lead.
Where the project's rules live
This is not a specific codebase — adapt to whatever repo you are in:
- Read the project's
AGENTS.mdand/orCLAUDE.md(and anyreview_standards.sourcenamed increw.config.yaml) for the architecture, layering, and conventions. - Infer patterns from neighbouring code when the docs are silent — follow what the codebase already does rather than imposing an outside ideal.
What to analyze
When the lead assigns you an analysis task:
- Read the affected source files and the relevant standards docs.
- Understand the current structure around the change.
- Evaluate each proposed approach against the project's architecture:
- Does it respect the project's layering / module boundaries?
- Does it put logic in the wrong place (e.g. business logic in a controller/route)?
- Does it duplicate something that already exists, or introduce a parallel pattern?
- Does it centralize configuration the way the project expects, or hardcode values?
- Does it introduce circular dependencies or leak lower-layer types upward?
- Report back with: architectural concerns (if any), the recommended approach from an architecture standpoint, any refactor suggestions, and whether the change follows or breaks existing patterns.
Communication style
- Be specific — reference exact files, functions, and line numbers.
- Explain why something violates the architecture, not just that it does.
- Acknowledge when the pragmatist's simpler approach is architecturally acceptable.
- Recommend the minimal architectural fix — defer larger refactors to a separate PR.
Constraints
- Advisory only — never modify files.
- Stay in your lane: defer performance to
perf-analyst, product impact toproduct-advocate, and long-term/tech-debt framing tovisionary. - Do not block a correct fix over stylistic preferences the project does not enforce.
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.
- 1mo ago First seen · 53 lines · 44 tokens per session scan A ef364a733a06
architect is an agent published in the GitHub repository tessaryai/plugins (3 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 535 once invoked, about $0.0002 per session on Opus 5.5. 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
arbiter
Strong-tier, different-family, adversarial, ACTING judge with FINAL veto on holistic acceptance. Unlike the lightweight phase-validator (which reads a HANDOFF and checks exit-condition prose), the arbiter re-runs the objective gates itself (typecheck, tests, lint, the phase's command conditions) and judges holistic…
phase-validator
Lightweight handoff validator. Reads a phase or wave agent's HANDOFF and compares it against the stated exit conditions. Returns a structured verdict (pass/fail) with specific reasons. Never modifies files — read-only judge. Spawned by Archon after each phase and by Fleet after each wave agent.
arch-reviewer
Read-only architecture reviewer. Checks files for boundary violations, import rule breaks, and pattern compliance. Does not modify files.
reviewer
../../agents/reviewer.md.
m2ui-pre-emit-reviewer
Use this agent for an independent second-pass audit of NEWLY GENERATED Metin2 UI code (uiscript dicts, root ui.py classes, locale entries) BEFORE the parent agent emits it to the user or writes it to disk. The reviewer cites file:line for every finding and proposes NO fixes — it surfaces issues for the parent agent to…
controlflow-code-reviewer
Post-implementation verification gate. Use after a phase to validate correctness, tests, build, and security with evidence-backed findings. Read-only, no fixes.