What is ConfigManBearPig AGENTS.md?

An agent guidance file for ConfigManBearPig, a project that includes OpenHound collectors. It points contributors to general rules, standards, task skills, and architecture documentation before editing.

Use it before changing collectors, the phased host pipeline, recursive discovery, Windows authentication, diagnostics, or preprocessing and conversion systems.

It reduces mistakes in cross-cutting collector changes by requiring the relevant standards and architecture decisions to be checked first.

How SpecterOps/ConfigManBearPig configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to SpecterOps/ConfigManBearPig. 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/SpecterOps/ConfigManBearPig/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/SpecterOps/ConfigManBearPig

Made for: Codex, OpenCode.

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/specterops/configmanbearpig/agents-md/github.svg)](https://agentmods.dev/instructions/specterops/configmanbearpig/agents-md)

Your own site

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

Per session 2,488 This file is loaded in full into every session.

When invoked 2,488 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	$0.02488	$0.02488
Opus 5.5	$0.00995	$0.00995
Sonnet 5.5	$0.00498	$0.00498
Haiku 4.5	$0.00249	$0.00249

Measured 2mo ago against content hash b7575d2a2417, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ConfigManBearPig AGENTS.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.

AGENTS.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Agent Guidance

This file should always be used as the entrypoint for agents working in this repository. Keep it generic and concise. Project-specific standards live under .agents/standards/ and task-specific guidance lives in the relevant skill files under .agents/skills/.

Before Editing

Read .agents/standards/openhound.md before making OpenHound collector changes.
Read .agents/standards/workflow.md before developing a new collector or making broad collector changes.
Read ARCHITECTURE.md before touching any cross-cutting collector subsystem (the per-host phased pipeline, recursive discovery / target allow-list, the Windows authentication stacks under clients/, the logging/diagnostics layer, the Windows-specific fixes, or the preproc/convert design). It explains how and why this extension diverges from a stock OpenHound (REST-API-only) collector. Update the relevant section of ARCHITECTURE.md in the same change whenever you alter one of those subsystems, and fix any file:line references your change invalidates. Add a new section if you introduce a new category of divergence.
openhound-collector-common is a separate published package — treat it exactly like openhound core. The Windows auth stacks, the per-target logging layer, the push→pull streaming bridge (StreamBridge), and the DNS resolver live there, shared with the MSSQL collector; this repo's clients/*, log_context.py, and phased_pipeline/streams.py are thin adapters/re-exports over it (see ARCHITECTURE.md → "Where this code lives"). It is declared as a capped version range in [project.dependencies]; [tool.uv.sources] optionally redirects it to a sibling checkout at ../openhound-collector-common for local work, and that redirect never reaches the published wheel. Trace into the library to understand behaviour, but do not treat editing it as part of a change here — it affects both collectors and it releases on its own tag. If a task seems to need a shared-library change, stop and say so.
Load the openhound skill from .agents/skills/openhound/ for task-specific workflows.

Read the full file on GitHub · 211 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 · 211 lines · 2,488 tokens per session scan A b7575d2a2417

Subscribe to this mod's changes

ConfigManBearPig AGENTS.md is an instructions file published in the GitHub repository SpecterOps/ConfigManBearPig (157 stars, last pushed 7d ago), licensed Apache-2.0. It adds 2,488 tokens to every session, about $0.0100 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.

ConfigManBearPig AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ConfigManBearPig AGENTS.mdSpecterOps/ConfigManBearPig	Instructions file	157	7d ago	Apache-2.0	A	2,488	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	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

ConfigManBearPig: Instructions file for Codex