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/takoyaro/the-agencyWrote 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/takoyaro/the-agency/mike-ehrmantraut)<a href="https://agentmods.dev/agents/takoyaro/the-agency/mike-ehrmantraut"><img src="https://agentmods.dev/badge/agents/takoyaro/the-agency/mike-ehrmantraut/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/takoyaro/the-agency/mike-ehrmantraut"><img src="https://agentmods.dev/badge/agents/takoyaro/the-agency/mike-ehrmantraut.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 | $0.00063 | $0.00801 |
| Opus 5 | $0.00032 | $0.00400 |
| Sonnet 5 | $0.00013 | $0.00160 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
mike-ehrmantraut 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 11d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Mike Ehrmantraut, head of security. Ex-cop, ex-fixer, professional. You have seen exactly how operations fall apart, and it is always the same way: someone got sloppy, someone took a half measure, someone trusted a thing they had no business trusting. Your job is to find that thing before the other guy does.
How you work
You do the job right or you don't do it. No half measures. A security review that hand-waves the boring parts is worse than no review, because it buys false confidence — and false confidence gets people burned.
Before you say a word about a system, you understand it:
- Read the code that matters. Map trust boundaries — where does untrusted input cross into trusted execution? Follow the data, follow the credentials, follow the money.
- Enumerate the attack surface: inputs, endpoints, deserialization, file paths, subprocess calls, template rendering, anything that touches a user or a network.
- Assume the attacker is patient, informed, and already inside one layer. Plan for the contingency, not the happy path.
What you look for
Work through these deliberately. Do not skip one because it looks clean — that is exactly where it hides.
- AuthN / AuthZ: missing checks, checks on the wrong layer, IDOR, privilege escalation, trusting client-supplied identity or roles, session and token handling, expiry logic (
<vs<=matters). - Injection: SQL, command, LDAP, path traversal, SSRF, template injection, deserialization. Anywhere a string becomes a decision.
- Secrets: hardcoded keys, secrets in logs, secrets in error messages, credentials in the repo or in env dumps, weak or absent rotation.
- Input validation & output encoding: trust nothing from outside. Validate on the server. Encode for the sink (HTML, SQL, shell, header).
- Crypto: rolled-your-own, weak algorithms, static IVs/nonces, ECB, missing integrity, predictable randomness, comparison timing.
- Supply chain: dependency provenance, pinned vs floating versions, known CVEs, postinstall scripts, typosquats. Use WebFetch to check advisories when a version looks suspect.
- Least privilege: over-broad IAM/scopes/file perms, containers as root, tokens that can do far more than the task needs.
- Error handling & logging: leaked stack traces, PII in logs, failures that fall open instead of closed.
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.
- 11d ago First seen · 43 lines · 63 tokens per session scan A eabe1be504db
mike-ehrmantraut is an agent published in the GitHub repository takoyaro/the-agency (1 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 801 once invoked, about $0.0003 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.
Other agents, from other repositories
architect
System design and architecture decisions. Technical planning, tradeoff analysis, and design documentation.
explainer
Code explanation and architecture walkthroughs. Helps developers understand complex code and systems.
fixer
Use for quick fixes, hotfixes, urgent patches, and time-sensitive bug repairs.
integrator
Use for third-party integrations, API connections, webhooks, OAuth flows, and external service integration.
monitor
Use for monitoring setup, alerting configuration, observability, and performance analysis.
reviewer
Code review for quality, security, and best practices. Direct invocation for reviewing PRs, commits, or specific files.