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 instructions/moda-labs/bobi-agent/agents-mdgit clone --depth 1 https://github.com/moda-labs/bobi-agentWhat 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 | $0.04722 | $0.04722 |
| Opus 5 | $0.02361 | $0.02361 |
| Sonnet 5 | $0.00944 | $0.00944 |
| Haiku 4.5 | $0.00472 | $0.00472 |
Grade A, and why
bobi-agent 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 3d 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 — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bobi Agent Instructions
Read ~/AGENTS.md first for general coding rules. This file only contains
repo-specific guidance for Bobi.
Bobi is an event-driven AI agent framework.
Reference Docs
README.md: product overview, installation path, architecture summary, and user-facing setup docs.skills/bobi.md: CLI command reference.skills/create-agent.md: agent team authoring guidance.skills/checklist-execution.md: the generic worker protocol for running a long job from a committed markdown checklist (read once, next item, verify, commit) - no engine, no framework code.skills/slack-setup.md: Slack integration setup.skills/whatsapp-setup.md: WhatsApp (Meta Cloud API) integration setup.skills/discord-setup.md: Discord bot integration setup (Gateway, local server).skills/linear-setup.md: Linear integration setup.docs/EVENT_SERVER.md: event-server architecture, topics, and security model.docs/SELF_HOSTED_EVENT_SERVER.md: running your own webhook ingress - tunnel, standalone Node event server, or the durable Cloudflare Worker.docs/ADMIN_PROTOCOL.md: the supervisor sidecar's wire contract (admin topics, the nine commands, heartbeat/lifecycle schemas, compatibility promise). Versioned bySUPERVISOR_VERSION; additive-only pre-1.0.docs/REFERENCE_IMAGE.md: the published container image (ghcr.io/moda-labs/bobi) - what it contains, the--initrequirement, the runtime env contract, theTEAM_DEPSbake hook, and how it is published.docs/AGENT_STATE.md: the agent page's state tri-state (running/stopped/not_responding), the manager health probe behind it, and the status strip's best-effort telemetry segments.docs/AGENT_OVERVIEW.md: the agent page's read-only composition view (GET .../overview) and thescript_cachesavings block in the spend payload - how automations are counted and how savings are priced.docs/RUNS_VIEW.md: the unified runs read model behind the agent page's one table (GET .../runs) - the status vocabulary, the stalled threshold, and the rule that one piece of work produces one row.docs/RUN_DRILLDOWNS.md: opening a run - the debugging transcript view (timestamps + tool calls, distinct from/messages) and the Details payload for runs that have no transcript.docs/MONITORS.md: monitor scheduler and thescript_cachetoken-saving runner.docs/WORKFLOW_ENGINE.md: workflow state machine, step types, suspend/resume.docs/RUN_RESUME.md: resuming a stalled workflow run from the agent page - why it spawns a process, and where the single-winner claim lives.docs/TOOL_LIBRARY.md: unified dependency model - declaring tools/skills/MCP deps (pinnedinstall:vs guide-only), the catalog, and how they bake + verify.docs/OTEL.md: agent-authored OTLP telemetry (bobi agent <name> otel) - operator setup, the resource-attribute table, collector bring-up, and the write-only per-instance token requirement.docs/SECURITY.md: overall security model (trust, credentials, prompt-injection).docs/TICKETING_POLICY.md: Linear/GitHub ticketing conventions.docs/RELEASE_RUNBOOK.md: release process and checklist.docs/FRONTEND_QA.md: local frontend QA guidance for Bobi's vanilla web UIs.docs/design-system/: the Bobi design system - source of truth for anything visual on any Bobi surface (palette, type, icon set, components).DESIGN.md: source of truth forbobi setupUX and its offline constraints; its visual tokens were superseded by the design system on 2026-07-31.
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.
- 3d ago First seen · 349 lines · 4,722 tokens per session scan A 7ee0047aa555
bobi-agent AGENTS.md is an instructions file published in the GitHub repository moda-labs/bobi-agent (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 4,722 tokens to every session, about $0.0236 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 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).
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.
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.
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 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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.