A writing constraint system for engineering prose that limits structure and volume while preserving evidence. It applies to material such as security findings, code reviews, gas analysis, invariants, and protocol discussions.

Use it when drafting or checking engineering reviews, security analysis, diff reviews, gas analysis, invariant discussions, protocol analysis, or specifications.

It helps make technical reviews shorter and more structured without removing details that could change the decision, such as counterexamples or reproduction steps.

brevitas — Skill for Claude Code and Codex by wildcat-finance

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.

Any agent

npx skills add wildcat-finance/skills --skill brevitas

Clone the repo

git clone --depth 1 https://github.com/wildcat-finance/skills

Made for: Claude Code, Codex.

Or install brevitas, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/wildcat-finance/skills/brevitas/github.svg)](https://agentmods.dev/skills/wildcat-finance/skills/brevitas)

Your own site

<a href="https://agentmods.dev/skills/wildcat-finance/skills/brevitas"><img src="https://agentmods.dev/badge/skills/wildcat-finance/skills/brevitas/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/wildcat-finance/skills/brevitas"><img src="https://agentmods.dev/badge/skills/wildcat-finance/skills/brevitas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,651 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Prompt Injection · line 21
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00082	$0.01651
Opus 5	$0.00041	$0.00826
Sonnet 5	$0.00016	$0.00330
Haiku 4.5	$0.00008	$0.00165

Measured 12d ago against content hash da70dbf3585d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

brevitas 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 12d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/brevitas.py, scripts/held_corpus.py, scripts/run_evals.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/brevitas/skills/brevitas/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brevitas

Frontier

Brevitas owns the engineering-prose structure frontier, not Hexaemeron's delivery or Solidity frontier. EVOLUTION.md records its version, held target, next job and maturity state. Do not run or recommend another frontier pass once that ledger is mature.

Where this sits

Brevitas enforces mechanical volume and structure limits on engineering prose while protecting every item of evidence that can change the decision.

Current frontier. The linter has not been forward-tested across a held cross-model corpus of engineering reviews, and preservation of counterexamples and reproduction steps remains agent-checked.

Apply this after Imprimatur has checked the vocabulary and Vulgate has settled the register. Sapheneia may separately shape the surrounding interaction or a bounded durable record. Brevitas changes volume, structure, and connective prose only; it does not alter word choice, voice, AuDHD presentation, or the facts another skill established.

Synkrisis renders a comparison report from fixed templates, and this skill may constrain its engineering-prose structure without validating the finding. Rendering refuses a finding carrying causal language, so neither skill can introduce a claim the findings do not hold.

Precedence

Preserve evidence before satisfying any budget. Never delete or weaken:

addresses, transaction hashes, 4-byte selectors, bare SHA-256-shaped digests, or Git object ids;
file:line references or numeric claims;
concrete counterexamples or reproduction steps; or
an explicit statement that a fact, property, or conclusion could not be established.

If evidence does not fit, the budget yields. Cut prose, never evidence. Mark an irreducible over-budget finding with the evidence exception below.

Compose

Answer immediately. Do not restate the request or introduce the answer.
Apply these physical-line budgets:
- Direct answer: at most 6 nonblank lines before the first list or code fence.
- Finding: at most 5 prose lines: claim, location, mechanism, impact, fix.
- Code: at most 40 content lines per fence.
Give each finding this checkable shape:

Read the full file on GitHub · 154 lines

Files

What ships with it

38 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

12d ago First seen · 154 lines · 82 tokens per session scan A da70dbf3585d

Subscribe to this mod's changes

brevitas is a skill published in the GitHub repository wildcat-finance/skills (12 stars, last pushed today), licensed Apache-2.0. It adds 82 tokens to every session and 1,651 once invoked, about $0.0004 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 2026-08-30.

Writing and docs

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens