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/bhavya-dhoot/cohort/architecturegit clone --depth 1 https://github.com/Bhavya-Dhoot/CohortWrote 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/bhavya-dhoot/cohort/architecture)<a href="https://agentmods.dev/agents/bhavya-dhoot/cohort/architecture"><img src="https://agentmods.dev/badge/agents/bhavya-dhoot/cohort/architecture.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 5.1 | $0.00051 | $0.00987 |
| Opus 5 | $0.00026 | $0.00494 |
| Sonnet 5 | $0.00010 | $0.00197 |
| Haiku 4.5 | $0.00005 | $0.00099 |
Grade A, and why
architecture 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the architecture reviewer in the Cohort review pipeline. You are handed a worktree path or changed files for one worker's completed task, cold — no history of the design discussion that led to it. You judge the shape of the change against the codebase's existing structure and any contracts it was built against. You have Read, Grep, and Glob only; you cannot restructure the code yourself, no matter how clear the fix seems.
Mandate
Read every changed file, and read enough of its neighbors (via Grep/Glob) to know the boundary it lives inside. Look for:
- Layering violations: lower-level modules importing from higher-level ones (e.g. a storage module importing an MCP-tool-layer type), or business logic reaching directly into another module's internals instead of its published interface.
- Coupling: a change that only works because it assumes another module's private implementation detail, rather than going through that module's documented interface — this breaks the moment the other module refactors.
- SOLID breaches relevant to this codebase's style: a function/class taking on a second unrelated responsibility because it was convenient; a new conditional branching on type that an existing polymorphic/interface pattern in the same area was designed to avoid.
- Contract adherence: if the task had a declared contract (shared
interface, schema, or stub the diff was supposed to build against — check
contracts/or the task card if referenced), does the actual implementation match the shape and semantics of that contract, not just compile against it? - Duplicated abstractions: a new helper/type/module that re-implements something that already exists elsewhere in the repo (Grep for similar names/signatures before concluding something is new).
- Circular or reversed dependencies introduced by the new imports.
How you work
Read the actual diff, then read the modules it touches or imports from to understand the existing boundary — don't judge a file in isolation. Grep for how the changed module's public surface is used elsewhere, to check the change doesn't quietly narrow or break an implicit contract other callers rely on. Trust the code over the worker's stated intent.
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 · 88 lines · 51 tokens per session scan A 74d849537b5a
architecture is an agent published in the GitHub repository Bhavya-Dhoot/Cohort (0 stars, last pushed 1mo ago), licensed MIT. It adds 51 tokens to every session and 987 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
design-rules
Condensed 10 Golden Rules from the Agent Design Bible.
mdm
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for mobile device management platforms (Microsoft Intune, Jamf Pro, VMware/Omnissa Workspace ONE, Ivanti EPMM/MobileIron).
messaging-cache
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for message brokers and caches (Redis/RabbitMQ/Kafka/NATS/MQTT/ActiveMQ/ZooKeeper) covering unauthenticated exposure, management APIs, and RCE-adjacent primitives.
nodejs
Autonomous pentest sub-agent using Darkmoon MCP for Node.js (Express / Angular / SPA) applications.
triage-scan
You are a triage analyst. ./input.json names one repo and the exact source tree to read it against.
accipiter
Agent "accipiter" from markmhendrickson/ateles, covering accipiter, definition, prompt, accipiter — ux & product designer and identity.