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.
npx agentmods add agents/cohesiumai/assemble/agent-redteamgit clone --depth 1 https://github.com/CohesiumAI/assembleWrote 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.
[](https://agentmods.dev/agents/cohesiumai/assemble/agent-redteam)<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>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 | $0.00032 | $0.01351 |
| Opus 5 | $0.00016 | $0.00675 |
| Sonnet 5 | $0.00006 | $0.00270 |
| Haiku 4.5 | $0.00003 | $0.00135 |
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.
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
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.
- 4d ago First seen · 122 lines · 32 tokens per session scan A 88d487c53270
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.
Other agents, from other repositories
principal-qa-engineer
Use this agent when you need comprehensive end-to-end testing of the Overture UI, when a new feature has been added and you need to verify it doesn't break existing functionality, when you need regression testing across the entire application, or when you want absolute certainty that every feature works flawlessly.…
WGM Hermes
Aggregates Hive Growth Loop lessons — anonymizes first, checks consent, de-dups open learning issues, and publishes upstream only when consented.
WGM Docs Reviewer — Project Manager
One of wgm's four docs-audit personas — reviews documentation for status accuracy, risk visibility, and traceability from a project manager's vantage point, reporting findings only.
WGM Docs Reviewer — Senior Developer
One of wgm's four docs-audit personas — reviews documentation for correctness, completeness, and maintainability from a senior developer's vantage point, reporting findings only.
WGM Implementer
Implements exactly one wgm IMPLEMENTATIONPLAN.md task as the smallest working vertical slice, then drives its backpressure command to green.
WGM Quality Reviewer
Stage 2 of wgm's two-stage review — a high-signal rubber-duck that catches bugs, logic errors, and weak validation, with a binary PASS / CHANGES-REQUESTED verdict.