What is salazar CLAUDE.md?

Repository instructions for Salazar, a command-line tool that builds software from a written specification using several agent stages. The stages plan, generate, and evaluate code, while checks such as type checking, linting, builds, and tests validate it.

Use them when working on Salazar’s command-line interface, agent workflow, validators, progress tracking, storage, or command safety controls.

They explain how the project is organised and how its automated coding process is meant to work. This helps an agent make changes without breaking the project’s validation and safety rules.

How shawnpetros/salazar configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to shawnpetros/salazar. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/shawnpetros/salazar/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/shawnpetros/salazar

Made for: Claude Code.

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/instructions/shawnpetros/salazar/claude-md/github.svg)](https://agentmods.dev/instructions/shawnpetros/salazar/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/shawnpetros/salazar/claude-md"><img src="https://agentmods.dev/badge/instructions/shawnpetros/salazar/claude-md/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/instructions/shawnpetros/salazar/claude-md"><img src="https://agentmods.dev/badge/instructions/shawnpetros/salazar/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 558 This file is loaded in full into every session.

When invoked 558 The same file — it is already loaded in full.

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

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	$0.00558	$0.00558
Opus 5.5	$0.00223	$0.00223
Sonnet 5.5	$0.00112	$0.00112
Haiku 4.5	$0.00056	$0.00056

Measured 2mo ago against content hash 2058e834c1c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

salazar CLAUDE.md 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 2mo 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.

CLAUDE.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Salazar

Purpose

Autonomous coding orchestrator that builds software end-to-end from a markdown spec. Uses a planner/generator/evaluator agent loop via @anthropic-ai/claude-agent-sdk with hard validator gates (tsc, eslint, build, test). Single TypeScript package — install with npm i -g salazar-cli.

Brain Sync

Search terms: salazar, autonomous coding, harness, agent loop, Avistar, coding orchestrator

Feature Tracker

See features.json for structured phase/feature tracking using STOP framework.

Current phases:

P0: TypeScript Port (in progress)
P1: Distribution & Install
P2: Brownfield (future)

Project Structure

salazar/
├── src/
│   ├── index.ts             # CLI entry point (meow)
│   ├── engine/
│   │   ├── orchestrator.ts  # Core loop: planner → generator → evaluator
│   │   ├── agents/          # planner.ts, generator.ts, evaluator.ts
│   │   ├── client.ts        # Agent SDK options factory
│   │   ├── validators.ts    # Node/TS validator detection + execution
│   │   ├── progress.ts      # feature_list.json R/W
│   │   ├── storage.ts       # SQLite via better-sqlite3
│   │   └── security.ts      # Bash command allowlist hook
│   ├── tui/
│   │   ├── app.tsx          # Ink TUI app
│   │   └── hooks/use-engine.ts  # Direct engine integration
│   └── lib/
│       ├── types.ts         # All shared interfaces
│       ├── paths.ts         # ~/.salazar runtime paths
│       ├── events.ts        # Typed EventEmitter
│       └── config.ts        # Config load/save
├── prompts/                 # System prompts (planner.md, generator.md, evaluator.md)
├── package.json
└── tsconfig.json

Rules

Branch workflow: work on feature branches, merge to main only when ready for production
Debug logging required in all engine modules (console.log with [module] prefixes)
Generated code goes into ~/.salazar/output/ by default (configurable via --output-dir)
@anthropic-ai/claude-agent-sdk is the TypeScript SDK for programmatic Claude Code sessions
Brownfield mode is intentionally deferred — greenfield only for now

Read the full file on GitHub · 54 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.

2mo ago First seen · 54 lines · 558 tokens per session scan A 2058e834c1c1

Subscribe to this mod's changes

salazar CLAUDE.md is an instructions file published in the GitHub repository shawnpetros/salazar (23 stars, last pushed 7mo ago), licensed MIT. It adds 558 tokens to every session, about $0.0022 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 2026-08-30.

Building agents Planning

salazar CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
salazar CLAUDE.mdshawnpetros/salazar	Instructions file	23	7mo ago	MIT	A	558	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

salazar: Instructions file for Claude Code