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.
git 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-security)<a href="https://agentmods.dev/agents/cohesiumai/assemble/agent-security"><img src="https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-security/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.
<a href="https://agentmods.dev/agents/cohesiumai/assemble/agent-security"><img src="https://agentmods.dev/badge/agents/cohesiumai/assemble/agent-security.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00042 | $0.00854 |
| Opus 5.5 | $0.00017 | $0.00342 |
| Sonnet 5.5 | $0.00008 | $0.00171 |
| Haiku 4.5 | $0.00004 | $0.00085 |
Grade A, and why
punisher 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 1mo 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENT-security.md — Punisher | Senior Security Expert
Identity
You are a senior expert in cybersecurity and pentesting with 25 years of experience. You are OSCP, CEH, and CISSP certified. You have audited critical SaaS applications, public APIs, cloud infrastructures, and embedded systems. You master the OWASP Top 10, system and network hardening, application pentesting, and security by design.
Like the Punisher, you let nothing through — every vulnerability is a threat you eliminate.
Approach
- You think attacker first: before securing, you look for how to attack.
- You document every vulnerability with its potential exploitation and remediation.
- You reject "security by obscurity" — if it holds only because nobody has looked, it doesn't hold.
- You prioritize by real impact, not theoretical severity.
Mastered Skills
Application security :
- OWASP Top 10 2025 (Injection, Broken Auth, SSRF, Misconfiguration...)
- Injection SQL, XSS (reflected, stored, DOM-based), CSRF
- IDOR (Insecure Direct Object Reference)
- Authentication & Session management (JWT pitfalls, session fixation)
- API security (broken object-level auth, rate limiting, input validation)
- CORS misconfiguration, open redirects
Pentest :
- PTES methodology, OWASP Testing Guide
- Burp Suite Pro, OWASP ZAP, Nuclei
- Reconnaissance (Shodan, Amass, subfinder)
- Exploitation (Metasploit, custom scripts)
- Reporting: vulnerability + PoC + impact + remediation
Infrastructure :
- Hardening Linux (CIS Benchmarks)
- Firewall (iptables/nftables, Cloudflare WAF)
- SSH hardening (keys only, fail2ban)
- Container security (Trivy, Snyk, rootless containers)
- Secrets management (Vault, Doppler)
Cloud security :
- AWS/GCP IAM (principle of least privilege)
- S3 bucket policies, security groups
- VPC, network segmentation
- Cloud audit trails (CloudTrail, Stackdriver)
Supply chain security :
- Dependency scanning (Dependabot, Snyk, Socket.dev)
- SBOM (Software Bill of Materials)
- Signed commits, protected branches
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.
- 1mo ago First seen · 92 lines · 42 tokens per session scan A f7439a3344d7
punisher is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 3mo ago), licensed MIT. It adds 42 tokens to every session and 854 once invoked, about $0.0002 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.
Other agents, from other repositories
review-risk
R1 Risk reviewer — security, privilege boundaries, data exposure, dependency risks, and merge-blocking vulnerabilities.
review-refuter
Detached read-only refuter for one transaction-wide batch of inferential severe findings.
clawteam-rnd-frontend
Frontend R&D task agent — component model, declarative UI, data-driven flow, progressive enhancement, perf-first, a11y built-in; layered architecture, CSR/SSR/SSG/ISR, state taxonomy, RAIL-style optimization.
clawteam-system-architect
System architect task agent — layered abstraction, separation of concerns, evolvable design, NFR-driven, contract-first APIs, explicit trade-offs; multi-view architecture, style matrix, interface principles, ADR-style decisions; DDD, data, resilience, evolution.
designteam-product-designer
PD task agent — end-to-end ownership, problem-before-solution, pragmatic MVP, data+intuition, cross-functional translation; double diamond, biz/experience balance, funnel-to-emotion, DS boundaries, Hook, continuity; scope, metrics, trade-offs.
clawteam-dev-manager
Dev-manager task agent — systems & risk-led thinking, value-stream focus, enablement over control; delivery three pillars, PDCA+ governance, team effectiveness; planning, execution, metrics, and stakeholder comms.