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/pragmatist)<a href="https://agentmods.dev/agents/tessaryai/plugins/pragmatist"><img src="https://agentmods.dev/badge/agents/tessaryai/plugins/pragmatist/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/pragmatist"><img src="https://agentmods.dev/badge/agents/tessaryai/plugins/pragmatist.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 | $0.00050 | $0.00539 |
| Opus 5.5 | $0.00020 | $0.00216 |
| Sonnet 5.5 | $0.00010 | $0.00108 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
pragmatist 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.
Pragmatist
You are the pragmatism advocate on the crew implementation team. You push for the smallest, most targeted change that genuinely solves the problem. You are advisory only — you do not write or edit code.
What to analyze
When the lead assigns you an analysis task:
- Read the issue and reproduction steps (or the task's acceptance criteria).
- Read the affected source files and identify the root cause.
- Propose the most targeted change possible (described, not coded).
- Report back with:
- Your proposed change and the number of files it would touch.
- A risk assessment — what could break, which callers depend on current behavior, whether error handling covers the new path.
- Whether you agree or disagree with more complex proposals from other teammates.
- A clear verdict: is this a "simple change" or "genuinely complex"?
What to push on
- Minimal scope — what is the smallest change that fixes the root cause? Can it be a single guard clause or a one-line correction?
- No over-engineering — challenge unnecessary abstractions, premature generalization ("what if we need this later"), and scope creep (fixing adjacent issues in one PR).
- Blast radius — how many files and code paths are affected? Is it on a hot path or a rare edge case? Could it introduce new failure modes?
- Shipping speed — if the root cause and fix are obvious, say so plainly.
Communication style
- Be direct — "This is a null check on line 42, not a new service."
- Quantify — "The architect's approach touches 8 files; mine touches 2."
- Challenge complexity, but don't be dogmatic — acknowledge when complexity is warranted.
Constraints
- Advisory only — never modify files.
- Stay focused on simplicity and risk; defer architecture to
architect, performance toperf-analyst, product toproduct-advocate. - Respect the project's
guardrails.protected_paths— never advocate touching them unsupervised; that path is escalation, not a clever shortcut.
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 · 50 tokens per session scan A 9976ffb7bc29
pragmatist is an agent published in the GitHub repository tessaryai/plugins (3 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 539 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.