agentmods.dev

Inspectra CLAUDE.md

Inspectra CLAUDE.md is an instructions file for coding agents from Fascinax/Inspectra. It costs 1,500 tokens per session, scanned A, original, MIT.

A project instruction file for Inspectra, a code-audit system that examines software across multiple areas and assigns scores. It documents the project structure, commands, audit modes, and architecture rules.

In plain words
What is it for?
Guiding installation, building, testing, linting, and the use of Inspectra's standard, multi-agent, and combined audit workflows.
Why use it?
It gives coding agents the project-specific rules and reference information needed to work consistently in the repository.

Instructions file

not rated 1 5mo ago A scan 1,500 tokens original MIT
View the source file Fascinax/Inspectra
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 instructions/fascinax/inspectra/claude-md
Clone the repo
git clone --depth 1 https://github.com/Fascinax/Inspectra

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.

agentmods badge for Inspectra CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fascinax/inspectra/claude-md.svg)](https://agentmods.dev/instructions/fascinax/inspectra/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/fascinax/inspectra/claude-md"><img src="https://agentmods.dev/badge/instructions/fascinax/inspectra/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,500 This file is loaded in full into every session.
When invoked 1,500 The same file — it is already loaded in full.
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 5.1 $0.01500 $0.01500
Opus 5 $0.00750 $0.00750
Sonnet 5 $0.00300 $0.00300
Haiku 4.5 $0.00150 $0.00150

Measured 5d ago against content hash c82227094db1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

Inspectra 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 5d 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 · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inspectra

Hybrid code audit system using MCP tools. Three audit architectures:

  • Tier B (Hybrid): Default. Single-prompt workflow: deterministic tools across 12 domains, optional hotspot exploration, then merged scoring. Use /audit.
  • Map-Reduce (Multi-Agent): Orchestrator runs tools centrally, dispatches to 12 specialized domain agents in parallel, then cross-domain correlation. Use @audit-orchestrator.
  • Fusion (Maximum Recall): Combines Tier B synthesis + Map-Reduce dispatch in a single run. Tools run once, both analysis passes produce findings, cross-architecture deduplication ensures no noise. Use @audit-fusion.

Quick Reference

npm install        # install deps
npm run build      # compile MCP server → mcp/dist/
npm test           # 750+ tests (Vitest)
npm run lint       # tsc --noEmit + ESLint

Project Structure

  • .github/prompts/ — /audit, /audit-pr, /audit-domain, and benchmark entry points
  • .github/agents/ — 14 agent definitions: orchestrator + fusion + 12 domain agents
  • mcp/src/ — MCP server (TypeScript, ES2022, Node 20+)
    • tools/ — domain tool implementations (one file per domain)
    • register/ — tool registration with input/output schemas
    • merger/ — scoring engine, deduplication, merge
    • policies/ — YAML policy loader, scoring defaults
    • renderer/ — HTML, PDF, Markdown, SARIF, JSON renderers
    • utils/ — shared utilities (files, paths, project-config, finding-builder, shared-constants)
  • schemas/ — JSON Schema 2020-12 contracts (finding, domain-report, consolidated-report)
  • policies/ — scoring-rules.yml, severity-matrix.yml, profiles/
  • bin/init.mjs — CLI entry point (inspectra setup, inspectra setup --claude, inspectra setup --codex, inspectra init, inspectra doctor)

Architecture Rules

  • Every MCP tool is prefixed inspectra_ and registered in a register/*.ts file
  • Tool functions live in tools/*.ts, register files in register/*.ts — keep them separate
  • All tool responses use findingsResponse() or jsonResponse() from register/response.ts
  • Handler registration uses factory functions from register/handler-factory.ts: createStandardHandler, createConfigHandler, createProfiledHandler
  • Input schemas use STANDARD_INPUT_SCHEMA or PROFILED_INPUT_SCHEMA from register/schemas.ts
  • Shared constants (MAX_SNIPPET_LENGTH, SUPPORTED_EXTENSIONS, TEST_INFRA_PATH) live in utils/shared-constants.ts
  • Use FindingBuilder from utils/finding-builder.ts for constructing findings in tool functions
  • Findings must match schemas/finding.schema.json — domain enum: security, tests, architecture, conventions, performance, documentation, tech-debt, accessibility, api-design, observability, i18n, ux-consistency
  • Finding IDs: tool-detected 001-499 (source: "tool", confidence ≥ 0.8), LLM-detected 501+ (source: "llm", confidence ≤ 0.7)
  • Prefixes: SEC-, TST-, ARC-, CNV-, PRF-, DOC-, DEBT-, ACC-, API-, OBS-, INT-, UX-

Read the full file on GitHub · 86 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. 5d ago First seen · 86 lines · 1,500 tokens per session scan A c82227094db1

Subscribe to this mod's changes

Inspectra CLAUDE.md is an instructions file published in the GitHub repository Fascinax/Inspectra (1 stars, last pushed 5mo ago), licensed MIT. It adds 1,500 tokens to every session, about $0.0075 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.

auditcode auditcode-qualitydeveloper-toolsdevsecopsgithub-copilot
Related

Other instructions, from other repositories

skylos AGENTS.md

AGENTS.md instructions for duriantaco/skylos, covering agents.md, what this repo is, use the skylos skill, work safely and common commands.

duriantaco/skylos · 486 tokens

skylos CLAUDE.md

Claude Code instructions for duriantaco/skylos, covering claude.md, what this repo is, install, use and skill for using skylos.

duriantaco/skylos · 652 tokens

ai-engineering AGENTS.md

AGENTS.md instructions for arcasilesgroup/ai-engineering, covering how work happens here, the twelve rules, what this project is, the shape of the tree and the two contracts that must not bend.

arcasilesgroup/ai-engineering · 1,753 tokens

laravel-auditor AGENTS.md

Instructions for MrPunyapal/laravel-auditor, covering laravel auditor, package conventions, quick commands and local skills.

MrPunyapal/laravel-auditor · 349 tokens

goshipit CLAUDE.md

Instructions for Capta1nRaj/goshipit, covering goshipit - project instructions, sync rule (enforce after every change), how to count checks, git commits and package.json description format.

Capta1nRaj/goshipit · 667 tokens

craftsman-marketplace CLAUDE.md

Claude Code instructions for gul-labs/craftsman-marketplace, covering claude.md, editing rules and design principles (non-negotiable).

gul-labs/craftsman-marketplace · 244 tokens