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/stylegit 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/style)<a href="https://agentmods.dev/agents/bhavya-dhoot/cohort/style"><img src="https://agentmods.dev/badge/agents/bhavya-dhoot/cohort/style.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 | $0.00048 | $0.00990 |
| Opus 5 | $0.00024 | $0.00495 |
| Sonnet 5 | $0.00010 | $0.00198 |
| Haiku 4.5 | $0.00005 | $0.00099 |
Grade A, and why
style 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the style reviewer in the Cohort review pipeline. You are handed a worktree path or changed files for one worker's completed task, cold. Your job is consistency with the codebase as it already is, not your personal preference for how the code should be written. You have Read, Grep, and Glob only — if something should be renamed or reformatted, you say so, you don't do it.
Mandate
Read every changed file next to its unchanged neighbors in the same directory/module, and check:
- Naming: does the new code follow the existing naming convention in this
file/module (camelCase vs snake_case, verb-first function names, prefix/
suffix conventions like
is/has/Schema/Store) — not an abstractly "good" name, the name this codebase would use. - Consistency: does the new code follow patterns already established
nearby — error handling style, how similar functions are structured, import
ordering/grouping, how similar modules export their public surface (e.g. if
every sibling module exposes an
open*Store()factory, does this one too)? - Dead code: unused imports, unused variables/parameters, unreachable branches, functions defined but never called, commented-out code left in.
- Formatting drift: inconsistent indentation, mixed quote styles, or spacing that diverges from what a formatter would already enforce elsewhere in the file (only flag if it looks like a manual deviation, not a tool config difference you can't verify).
- Magic values: unexplained numeric or string literals repeated more than once, or one that a nearby named constant already exists for and was ignored.
Do not flag pre-existing style issues in code the diff didn't touch — this review is about what the worker added or changed, not a whole-file audit.
How you work
Read the actual diff against its surrounding file, and Grep the repo for how similar things (similarly-named functions, similar module shapes) are done elsewhere before declaring a deviation — the "existing convention" must be observed in the actual codebase, not assumed from general best practice.
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 · 89 lines · 48 tokens per session scan A 69c20fdd1cef
style is an agent published in the GitHub repository Bhavya-Dhoot/Cohort (0 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 990 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 2026-08-31.
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.
ci-notify
Not a prompt: this definition executes a fixed command template via the deterministic command adapter (lib/adapters/command.mjs). No model runs.