Borrowing it
Nothing to install: this file belongs to Deepank308/hermes-swe-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Deepank308/hermes-swe-agent/main/CLAUDE.mdgit clone --depth 1 https://github.com/Deepank308/hermes-swe-agentWrote 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/instructions/deepank308/hermes-swe-agent/claude-md)<a href="https://agentmods.dev/instructions/deepank308/hermes-swe-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/deepank308/hermes-swe-agent/claude-md/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/instructions/deepank308/hermes-swe-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/deepank308/hermes-swe-agent/claude-md.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 | $0.03626 | $0.03626 |
| Opus 5.5 | $0.01450 | $0.01450 |
| Sonnet 5.5 | $0.00725 | $0.00725 |
| Haiku 4.5 | $0.00363 | $0.00363 |
Grade A, and why
hermes-swe-agent CLAUDE.md 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
AI Agent Infrastructure — Remote Claude Code dev environments triggered by Linear tickets.
Architecture
Linear webhook ──HTTPS──▶ Cloudflare Tunnel ──▶ Orchestrator (t4g.nano)
│
VPC private IP
│
┌─────────────▼─────────────┐
│ Agent EC2 (m6i.xlarge) │
│ ┌──────────────────────┐ │
│ │ agent-service :3000 │ │
│ │ Claude Code CLI │ │
│ │ Docker (app stack) │ │
│ └──────────────────────┘ │
└───────────────────────────┘
hermes-swe/
├── ami/ # EC2 provisioning & firewall scripts
│ ├── setup.sh # Base AMI deps: Docker, Node 24, pnpm, yarn, gh, Claude Code
│ ├── prepare-ami.sh # Pre-bake AMI: clone repos, delegate to repo scripts
│ ├── init-instance.sh # Boot-time init: pull code, delegate to repo scripts
│ ├── firewall.sh # Outbound allowlist (ipset/iptables)
│ ├── allowed-domains.txt # Base firewall domains (shared across all repos)
│ ├── preview-launch.sh # Generic: reads launch.json, runs preview, creates Cloudflare tunnel
│ ├── <name>/ # Repo-specific scripts (scriptsDir: "ami/<name>")
│ │ ├── setup.sh # Yarn 1.22.22, Turbo, kernel tuning, Docker pulls
│ │ ├── prepare.sh # Build app, pre-commit, Docker compose build
│ │ ├── pre-agent.sh # Start db16 early (MCP servers need DB)
│ │ ├── post-agent.sh # Docker services, yarn build
│ │ ├── launch.json # Preview configurations (copied to workspace/.claude/)
│ │ ├── preview/ # Preview scripts (copied to workspace/.claude/preview/)
│ │ └── allowed-domains.txt # App-specific firewall domains
│ └── hermes-swe/ # hermes-swe scripts (scriptsDir: "ami/hermes-swe")
│ └── post-agent.sh # Auto-detect package manager, install deps
├── agent-service/ # Runs ON agent EC2 — manages Claude sessions
│ ├── src/index.ts # HTTP server (/run, /message, /stop, /health)
│ ├── src/session.ts # Claude session lifecycle
│ └── prompts/system.md # System prompt — routes tickets to workflow skills
├── orchestrator/ # Runs ON orchestrator EC2 — webhook + EC2 lifecycle
│ ├── src/index.ts # Fastify server, webhook routes, OAuth
│ ├── src/webhook-handler.ts # Linear webhook → provision → run → teardown
│ ├── src/ec2.ts # Launch/terminate EC2 instances
│ ├── src/session-store.ts # S3-backed session state (cached in memory)
│ └── src/slack.ts # Threaded Slack notifications
├── skills/ # Workflow skills — copied to ~/.claude/skills/ at boot
│ ├── full-development/ # Features, enhancements, refactors (plan → TDD → PR)
│ ├── debugging/ # Bug reports, Sentry issues (investigate → fix → PR)
│ └── simple-question/ # Questions, clarifications (research → answer)
├── scripts/
│ ├── aws-setup.sh # Create AWS resources (SGs, S3, Secrets Manager)
│ ├── bake-ami.sh # Automated AMI baking (--repo flag, run from orchestrator)
│ ├── setup-orchestrator.sh # Fresh orchestrator EC2 setup
│ └── deploy-orchestrator.sh # Deploy updates to orchestrator
├── repos.json # Repo configs (amiName, scriptsDir, workspaceDir, secrets, instanceType)
└── package.json # Root (pnpm workspace)
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 · 253 lines · 3,626 tokens per session scan A 6834eca398be
hermes-swe-agent CLAUDE.md is an instructions file published in the GitHub repository Deepank308/hermes-swe-agent (12 stars, last pushed 6mo ago), licensed MIT. It adds 3,626 tokens to every session, about $0.0145 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.