Borrowing it
Nothing to install: this file belongs to tellahq/opensession. 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/tellahq/opensession/main/AGENTS.mdgit clone --depth 1 https://github.com/tellahq/opensessionWrote 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/tellahq/opensession/agents-md)<a href="https://agentmods.dev/instructions/tellahq/opensession/agents-md"><img src="https://agentmods.dev/badge/instructions/tellahq/opensession/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/tellahq/opensession/agents-md"><img src="https://agentmods.dev/badge/instructions/tellahq/opensession/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 | $0.02929 | $0.02929 |
| Opus 5.5 | $0.01172 | $0.01172 |
| Sonnet 5.5 | $0.00586 | $0.00586 |
| Haiku 4.5 | $0.00293 | $0.00293 |
Grade B, and why
opensession AGENTS.md scanned grade B with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Use the full root deploy, `sudo deploy/deploy.sh <sha>`, instead when a change Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
`Bun.spawnSync`, or synchronous SQLite still violates this rule. Never add a How it starts
The opening of the file, as written. The whole thing — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Default to Bun instead of Node.js.
Keep instance-private operator instructions in an untracked AGENTS.local.md or
CLAUDE.local.md, never in this file.
Public repository
This repository is public. Everything that lands here is readable by anyone:
commits, branch names, PR titles and bodies, review comments, issues, code,
docs, tests, fixtures, and screenshots. Never put private organization
information in any of them: internal hostnames, URLs, or paths, private
repositories' names or code, teammate or customer details, secrets, internal
plans, or anything taken from memory, Slack, Linear, local instructions, or
the session context. Describe what a change does in terms of this repository
alone. The session attribution footer and the Co-authored-by trailer are the
only exception. Use placeholder names (acme, example.test) in examples and
tests.
Publishing to repositories
Repositories owned by your own organization are fair game, including public ones: commit, push, and open issues, comments, and pull requests there as part of normal work.
For any repository outside your organization, public or third-party, never publish without explicit user confirmation in the current conversation. Local investigation and commits are allowed; issues, comments, branches, forks, pushes, and pull requests are not.
Choose the client first
Open Session has five clients:
- Web UI:
packages/core/opensession-server/src/frontend/ - Phone web/PWA: the same web bundle at phone width
- Electron shell:
packages/clients/mac/ - Native Swift app:
packages/clients/ios/ - Chrome extension:
packages/clients/chrome/
Once a conversation names a client, keep working on that client unless the user
changes scope. Ask when the target is unclear. For web changes, build desktop
and phone together. For protocol, preference, or transcript changes, check the
native app and Chrome extension for matching wire models or behavior. Read the
nearest nested AGENTS.md before editing a client.
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 Changed · +13 lines · +152 tokens per session 8dacab9b232c
- 1mo ago Changed · +6 lines · +88 tokens per session e171bb6f2963
- 1mo ago Changed · +29 lines · +292 tokens per session 366f972911b5
- 1mo ago Changed · +8 lines · +108 tokens per session 6918eaea4b48
- 1mo ago Changed · +19 lines · +324 tokens per session 0f777c6f3f3c
- 1mo ago First seen · 169 lines · 1,965 tokens per session scan B d1988bb35d62
opensession AGENTS.md is an instructions file published in the GitHub repository tellahq/opensession (399 stars, last pushed today), licensed MIT. It adds 2,929 tokens to every session, about $0.0117 per session on Opus 5.5. A static security scan graded it B with 2 findings (asks for root, runs shell commands). 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.