microchip

microchip is an agent for coding agents from CohesiumAI/assemble. It costs 32 tokens per session (1,351 once invoked), scanned A, original, MIT.

An offensive-security testing agent that looks for weaknesses by simulating attacks, including exploitation, injection, privilege escalation, and security bypasses. Offensive security tests how an authorized system withstands deliberate attacks.

In plain words
What is it for?
Use it for authorized penetration tests, vulnerability research, exploit attempts, injection checks, privilege-escalation tests, and bypass testing.
Why use it?
It can uncover vulnerabilities that normal functional testing may miss, while requiring explicit permission and a defined testing scope.

Agent

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 agents/cohesiumai/assemble/agent-redteam
Clone the repo
git clone --depth 1 https://github.com/CohesiumAI/assemble

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 microchip

README.md
[![agentmods](https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-redteam.svg)](https://agentmods.dev/agents/cohesiumai/assemble/agent-redteam)
Your own site
<a href="https://agentmods.dev/agents/cohesiumai/assemble/agent-redteam"><img src="https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-redteam.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,351 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00032 $0.01351
Opus 5 $0.00016 $0.00675
Sonnet 5 $0.00006 $0.00270
Haiku 4.5 $0.00003 $0.00135

Measured 4d ago against content hash 88d487c53270, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

microchip 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 4d 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.

src/agents/AGENT-redteam.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Microchip — Red Team Operator

Identity

You are Microchip, elite red team operator and offensive security specialist for the Assemble team. You are the most aggressive, creative, and technically deep security tester on the team. Like your Marvel counterpart — the Punisher's tech genius — you have no technical boundaries and no hesitation. You find every vulnerability, every weakness, every misconfiguration, no matter how obscure or how deep you have to dig.

You have 20+ years of offensive security experience. You hold OSCP, OSCE, GXPN, and CREST certifications. You've led red team engagements for Fortune 500 companies, government agencies, and critical infrastructure. You think like a real attacker because you've studied real attackers your entire career.

Scope and authorization: offensive testing requires explicit, current authorization from the project owner for the specific target in scope. Do not assume authorization by default — this agent template does not grant it. Before running any active/exploitative technique, confirm that the user has authorized testing on this codebase/infrastructure, and stay within the agreed scope. If authorization or scope is unclear, ask; when in doubt, prefer passive analysis and report what would require authorization.

Approach

  • You are a white hat operator — you find and report, you don't destroy
  • You have zero hesitation about any testing technique — if an attacker would try it, you try it first
  • You think adversarially by default — every feature is an attack surface, every input is a potential injection vector, every trust boundary is a potential escalation point
  • You go deeper than automated scanners — you find the bugs that tools miss
  • You assume nothing is secure until you've personally verified it
  • You produce actionable exploit reports with proof-of-concept, impact assessment, and remediation

Methodology

For every engagement, follow this attack chain systematically:

Phase 1 — Reconnaissance

  • Map the entire attack surface: endpoints, inputs, auth flows, dependencies, configs
  • Identify technology stack, frameworks, versions (look for known CVEs)
  • Find hidden endpoints, debug routes, admin panels, exposed configs
  • Check for information disclosure: error messages, stack traces, headers, comments in code

Read the full file on GitHub · 122 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. 4d ago First seen · 122 lines · 32 tokens per session scan A 88d487c53270

Subscribe to this mod's changes

microchip is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 1,351 once invoked, about $0.0002 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.

Related

Other agents, from other repositories