What is clude AGENTS.md?

Repository instructions for Clude, a bot, including its related gstack workflow tools and a required memory system. They define how agents should recall and save project information and how work moves through staging.

Using the listed workflow commands, recalling relevant project memories, recording decisions and findings, and following the required staging process.

They preserve useful context between conversations and set shared rules for browsing, planning, reviewing, testing, and releasing work.

clude AGENTS.md — Instructions file by sebbsssss

Install

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.

agentmods

npx agentmods add instructions/sebbsssss/clude/agents-md

Clone the repo

git clone --depth 1 https://github.com/sebbsssss/clude

Made for: Codex, OpenCode.

Per session 486 This file is loaded in full into every session.

When invoked 486 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00486	$0.00486
Opus 5	$0.00243	$0.00243
Sonnet 5	$0.00097	$0.00097
Haiku 4.5	$0.00049	$0.00049

Measured 2d ago against content hash fbffed7ff204, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clude 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 2d 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.

AGENTS.md · 35 lines

What it actually says

Clude Bot

gstack

Use the /browse skill from gstack for all web browsing. Never use mcp__claude-in-chrome__* tools.

Available skills: /office-hours, /plan-ceo-review, /plan-eng-review, /plan-design-review, /design-consultation, /review, /ship, /browse, /qa, /qa-only, /design-review, /setup-browser-cookies, /retro, /investigate, /document-release, /codex, /careful, /freeze, /guard, /unfreeze, /gstack-upgrade.

Clude Memory (Required for ALL agents)

Clude is our product. Every agent MUST actively use it. The clude-memory MCP server is configured in .mcp.json.

Every heartbeat / conversation, you MUST:

Store memories about your work: decisions made, findings, blockers, task outcomes, things learned. Use store_memory with source: "mcp:<your-role>" (e.g. mcp:ceo, mcp:lead-pm, mcp:researcher).
Recall memories when starting work on a topic you may have context on. Use recall_memories before diving in.
Minimum 1 memory per heartbeat where you do meaningful work. More is better.

Memory type guide:

episodic — events, task completions, meetings, incidents
semantic — facts, knowledge, architecture decisions, team info
procedural — how-to knowledge, workflows, patterns that work
self_model — reflections on your own performance, strengths, gaps

Always include: meaningful tags, importance (0-1), and summary. This is our product — dogfood it seriously.

Staging Workflow (Required)

All changes go through staging first. See CLAUDE.md for the full workflow.

Key rules for all agents:

All PRs target staging, never main
No direct pushes to main or staging
Board verifies at cludebot-test-preview.up.railway.app before approving merge to main
When shipping, always set base branch to staging

Changes

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.

2d ago First seen · 35 lines · 486 tokens per session scan A fbffed7ff204

Subscribe to this mod's changes

clude AGENTS.md is an instructions file published in the GitHub repository sebbsssss/clude (21 stars, last pushed 1mo ago), licensed MIT. It adds 486 tokens to every session, about $0.0024 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.

Memory and context Productivity

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

clude AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Clude Bot

gstack

Clude Memory (Required for ALL agents)

Staging Workflow (Required)

What this file has done since we first saw it

Other instructions, from other repositories

codex AGENTS.md

vscode buildNext.instructions.md

next.js AGENTS.md

vscode oss-third-party-notices.instructions.md

spec-kit AGENTS.md

langchain AGENTS.md