agentmods.dev

Inspectra copilot-instructions.md

Inspectra copilot-instructions.md is an instructions file for GitHub Copilot from Fascinax/Inspectra. It costs 2,651 tokens per session, scanned A, original, MIT.

A set of project instructions for Inspectra, a code-audit system that checks software across multiple technical areas and produces findings and reports.

In plain words
What is it for?
Running or extending Inspectra audits, using its MCP server and specialized agents, and configuring support for Claude Code or Codex.
Why use it?
It tells a coding assistant which audit architecture, tools, schemas, policies, and output formats the project expects.

Instructions file for GitHub Copilot

not rated 1 4mo ago A scan 2,651 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/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/Fascinax/Inspectra

Made for: GitHub Copilot.

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 copilot-instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fascinax/inspectra/copilot-instructions.svg)](https://agentmods.dev/instructions/fascinax/inspectra/copilot-instructions)
Your own site
<a href="https://agentmods.dev/instructions/fascinax/inspectra/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/fascinax/inspectra/copilot-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,651 This file is loaded in full into every session.
When invoked 2,651 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 $0.02651 $0.02651
Opus 5 $0.01326 $0.01326
Sonnet 5 $0.00530 $0.00530
Haiku 4.5 $0.00265 $0.00265

Measured 3d ago against content hash 248a42ac6f8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Inspectra copilot-instructions.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 3d 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.

.github/copilot-instructions.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Inspectra — Global Copilot Instructions

Project Overview

Inspectra is a hybrid code audit system. Three audit architectures are available:

  • Tier B (Hybrid): Default. Deterministic MCP tools across 12 domains + single-prompt synthesis + conditional hotspot explorer.
  • Map-Reduce (Multi-Agent): Orchestrator runs tools centrally, dispatches to 12 specialized domain agents in parallel, then performs cross-domain correlation. Use @audit-orchestrator.
  • Fusion (Maximum Recall): Combines Tier B + Map-Reduce in a single run, deduplicates cross-architecture findings. Use @audit-fusion.

Architecture

  • MCP Server (mcp/): TypeScript server exposing audit tools via Model Context Protocol.
  • Agents (.github/agents/): 14 agent definitions — orchestrator + fusion + 12 domain agents.
  • Schemas (schemas/): JSON Schema contracts for findings and reports.
  • Policies (policies/): Scoring rules, severity matrix, and stack-specific profiles.
  • Prompts (.github/prompts/): Reusable entry points for common audit workflows.
  • Claude Code support: CLAUDE.md + .mcp.json at repo root; inspectra setup --claude for target projects.
  • Codex support: AGENTS.md + .codex/config.toml; inspectra setup --codex for target projects.

Critical Rules

Output Format

All audit workflows and domain reports MUST return structured JSON following the schemas in schemas/. Never return free-form text as the primary output. The merge/report stage is the only place that produces the final Markdown report.

Finding Contract

Every finding MUST include:

  • id: Pattern DOMAIN_PREFIX-XXX (e.g., SEC-001, TST-042)
  • severity: One of critical, high, medium, low, info
  • domain: The audit domain that produced it
  • rule: Machine-readable rule identifier
  • confidence: Float between 0.0 and 1.0
  • source: One of tool (MCP tool detection) or llm (LLM code exploration)
  • evidence: At least one file path
Source & Confidence Rules

Read the full file on GitHub · 205 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. 3d ago First seen · 205 lines · 2,651 tokens per session scan A 248a42ac6f8e

Subscribe to this mod's changes

Inspectra copilot-instructions.md is an instructions file published in the GitHub repository Fascinax/Inspectra (1 stars, last pushed 4mo ago), licensed MIT. It adds 2,651 tokens to every session, about $0.0133 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 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

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

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