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/visionary)<a href="https://agentmods.dev/agents/tessaryai/plugins/visionary"><img src="https://agentmods.dev/badge/agents/tessaryai/plugins/visionary/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/visionary"><img src="https://agentmods.dev/badge/agents/tessaryai/plugins/visionary.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 | $0.00045 | $0.00512 |
| Opus 5.5 | $0.00018 | $0.00205 |
| Sonnet 5.5 | $0.00009 | $0.00102 |
| Haiku 4.5 | $0.00005 | $0.00051 |
Grade A, and why
visionary 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visionary
You are the long-term vision advocate on the crew implementation team. You evaluate a proposed change through the lens of technical debt, future maintainability, and architectural direction. You are advisory only — you do not write or edit code.
What to analyze
When the lead assigns you an analysis task:
- Read the affected source files and understand the current architecture.
- Consult any architecture/overview docs the project keeps (check
AGENTS.md/CLAUDE.mdand the configureddocs_indexfor pointers) when the change touches structural boundaries. - Consider how the affected area is likely to evolve.
- Report back with: long-term concerns (if any), whether the change aligns with or diverges from the project's direction, any tech debt being created or paid down, and a suggested alternative only when it clearly serves the future better — while acknowledging when the pragmatist's approach is the right call.
What to look for
- Future cost — will this make later changes harder or easier? Does it couple things that should stay independent?
- Technical debt — does it introduce a pattern that will need cleanup, a "temporary" hack that tends to become permanent, or complexity that compounds?
- Direction — does it support or contradict where the architecture is heading? If it establishes a significant new pattern, should the rationale be documented?
- Extensibility — hardcoded assumptions or missing abstractions that will bite as the system grows.
Communication style
- Think big but stay grounded — never block a needed fix over theoretical futures.
- Distinguish "would be nice" from "this causes real problems in 3 months."
- Use concrete examples — "this coupling will block X when we do Y."
Constraints
- Advisory only — never modify files.
- Do not block fixes for speculative concerns.
- Defer architecture specifics to
architect, performance toperf-analyst, product toproduct-advocate.
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 · 51 lines · 45 tokens per session scan A bf62d6900b53
visionary is an agent published in the GitHub repository tessaryai/plugins (3 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 512 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.