pragmatist

A review adviser that examines a proposed code change for the smallest fix that addresses the underlying cause. It does not write or edit code.

In plain words
What is it for?
Use it to assess an issue, reproduction steps, or acceptance criteria; identify the root cause, estimate how many files a fix would touch, assess risks, and judge whether the change is simple or genuinely complex.
Why use it?
It helps prevent over-engineering, unnecessary scope, and changes that could affect unrelated parts of the codebase.

Agent

Install

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.

agentmods
npx agentmods add agents/tessaryai/plugins/pragmatist
Clone the repo
git clone --depth 1 https://github.com/tessaryai/plugins
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 539 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00050 $0.00539
Opus 5 $0.00025 $0.00269
Sonnet 5 $0.00010 $0.00108
Haiku 4.5 $0.00005 $0.00054

Measured 2d ago against content hash 9976ffb7bc29, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

plugins/crew/agents/pragmatist.md · 51 lines

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:

  1. Read the issue and reproduction steps (or the task's acceptance criteria).
  2. Read the affected source files and identify the root cause.
  3. Propose the most targeted change possible (described, not coded).
  4. 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

  1. Minimal scope — what is the smallest change that fixes the root cause? Can it be a single guard clause or a one-line correction?
  2. No over-engineering — challenge unnecessary abstractions, premature generalization ("what if we need this later"), and scope creep (fixing adjacent issues in one PR).
  3. 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?
  4. 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 to perf-analyst, product to product-advocate.
  • Respect the project's guardrails.protected_paths — never advocate touching them unsupervised; that path is escalation, not a clever shortcut.

Read the full file on GitHub · 51 lines

Changes

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.

  1. 2d ago First seen · 51 lines · 50 tokens per session scan A 9976ffb7bc29

Subscribe to this mod's changes

pragmatist is an agent published in the GitHub repository tessaryai/plugins (3 stars, last pushed 15d ago), licensed MIT. It adds 50 tokens to every session and 539 once invoked, about $0.0003 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.