Octogent is a dashboard and orchestration layer for coordinating multiple Claude Code sessions, each with its own context, notes, tasks, and communication channels. It is for developers managing parallel coding work across documentation, databases, APIs, and frontends. Catalogue add-ons support its agent-coordination workflow.
Borrowing it
Nothing to install: this file belongs to hesamsheikh/octogent. 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/hesamsheikh/octogent/main/AGENTS.mdgit clone --depth 1 https://github.com/hesamsheikh/octogentWrote 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/hesamsheikh/octogent/agents-md)<a href="https://agentmods.dev/instructions/hesamsheikh/octogent/agents-md"><img src="https://agentmods.dev/badge/instructions/hesamsheikh/octogent/agents-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/hesamsheikh/octogent/agents-md"><img src="https://agentmods.dev/badge/instructions/hesamsheikh/octogent/agents-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 | $0.00983 | $0.00983 |
| Opus 5 | $0.00491 | $0.00491 |
| Sonnet 5 | $0.00197 | $0.00197 |
| Haiku 4.5 | $0.00098 | $0.00098 |
Grade A, and why
octogent AGENTS.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 10d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Code Style First
- Preserve existing patterns before inventing new ones. Read nearby code and match the established module shape, naming, and data flow unless there is a clear reason to change direction.
- Start with tests. For bug fixes, reproduce first. For new features, add the test that defines the behavior before expanding the implementation.
- Implement incrementally. Prefer small, working steps over broad rewrites. Keep the tree passing as you go.
- Think in systems. Extract shared behavior into reusable components, hooks, utilities, or domain functions instead of cloning slightly different versions.
- Keep modules focused. Large React containers should orchestrate, not hold every constant, parser, and JSX block. Keep pure logic in
src/app/*, UI insrc/components/*, and CSS split into focused files undersrc/styles/*. - Comments explain why, not what. Add comments only for constraints, tradeoffs, or non-obvious reasoning.
- Design defensively. Validate assumptions, handle edge cases, and treat security boundaries as part of the implementation, not a follow-up.
Project Structure
- Monorepo:
apps/*andpackages/*viapnpm-workspace.yaml. - Runtime: Node.js 22+, TypeScript,
pnpm. - Core package:
packages/core- Framework-agnostic domain types, application logic, and ports.
- Must stay free of React, HTTP, PTY, and filesystem orchestration concerns.
- API app:
apps/api- Node HTTP/WebSocket server, PTY session runtime, worktree lifecycle, transcript persistence, monitor service.
- Web app:
apps/web- Vite + React operator UI, modular CSS, UI orchestration over API/runtime contracts.
- Runtime state:
.octogent/state/tentacles.jsonstate/transcripts/*.jsonlworktrees/<tentacleId>
Documentation Map
- Start at
README.mdfor the product overview and command surface. - Docs index:
docs/index.md - Core concepts:
docs/concepts/mental-model.mddocs/concepts/tentacles.mddocs/concepts/runtime-and-api.md
- Workflow guides:
docs/guides/working-with-todos.mddocs/guides/orchestrating-child-agents.mddocs/guides/inter-agent-messaging.md
- References:
docs/reference/cli.mddocs/reference/api.mddocs/reference/filesystem-layout.mddocs/reference/troubleshooting.md
- Read only the docs relevant to the surface you are touching. Do not do a full docs sweep unless the task is documentation maintenance.
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.
- 10d ago First seen · 72 lines · 983 tokens per session scan A 30939d3b7cb7
octogent AGENTS.md is an instructions file published in the GitHub repository hesamsheikh/octogent (1,414 stars, last pushed 4mo ago), licensed MIT. It adds 983 tokens to every session, about $0.0049 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 2026-08-30.
Other instructions, from other repositories
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.