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/sixb-ai/sixb/agents-mdgit clone --depth 1 https://github.com/sixb-ai/sixbWrote 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/sixb-ai/sixb/agents-md)<a href="https://agentmods.dev/instructions/sixb-ai/sixb/agents-md"><img src="https://agentmods.dev/badge/instructions/sixb-ai/sixb/agents-md.svg" alt="Measured on agentmods" 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 | $0.03044 | $0.03044 |
| Opus 5 | $0.01522 | $0.01522 |
| Sonnet 5 | $0.00609 | $0.00609 |
| Haiku 4.5 | $0.00304 | $0.00304 |
Grade A, and why
sixb 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 4d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Repo-wide agent instructions for sixb.
Scope
- This file applies to the whole repository unless a nearer
AGENTS.mdis added later. - Keep one root
AGENTS.mdfor now. Add nested files only when a package genuinely needs different instructions.
Repo Map
packages/core: runtime, ontology builders, providers, and validationpackages/server: Elysia HTTP/WebSocket API and OpenAPI generationpackages/atlas: built-in React UI (the Atlas app); pages live insrc/pages/packages/ui: shared React component library used by Atlaspackages/client: generated typed client artifactspackages/cli: CLI entrypoint forsixbpackages/create-sixb: zero-dependency project scaffolder and templatepackages/app: custom app integrationconnectors/,storage/,broker/: integrations and infrastructure providersexamples/: runnable sample projects
Toolchain
- Bun only for package management, scripts, and runtime. Do not use
npm,pnpm,yarn, or Vite CLI commands. - TypeScript is
strict, targets ES2022, uses ESNext modules, andmoduleResolution: "bundler". - Formatting and linting are enforced with Biome.
- Prefer
rgandrg --filesfor search.
Core Commands
Repo-wide:
bun install
bun run build
bun run typecheck
bun run test
bun run test:e2e
bun run test:all
bun run check
bun run check:fix
bun run generate:client
bun sixb dev
bun create-sixb my-app
Targeted:
bun --filter @sixb/core build
bun --filter @sixb/core typecheck
bun test packages/core/tests/create-sixb.test.ts
bun test packages/server/tests/
CI runs these as independent parallel jobs (each does bun install --frozen-lockfile first):
typecheck:bun run typecheckbuild:bun run build, thenbun run test:publishclient:bun run generate:client, thengit diff --exit-codetest:bun run test:cilint:bun run checke2e: package-scoped matrix jobs for packages withtest:e2e
test:ci is bun test wrapped in scripts/ci-guard.ts, which fails the run at the first 60-second
silence and prints the last test file, the process tree, and each thread's kernel wait state. The
job's timeout-minutes is only a backstop: a job that dies at its own wall clock reports
"cancelled" with the log ending mid-stream, which is indistinguishable from every other cause. The
guard exists because a Bun.build() deadlock once cost five 15-minute runs before anyone found the
one named failure buried in the log.
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.
- 4d ago First seen · 192 lines · 3,044 tokens per session scan A d4ca7024ef63
sixb AGENTS.md is an instructions file published in the GitHub repository sixb-ai/sixb (53 stars, last pushed 4d ago), licensed MIT. It adds 3,044 tokens to every session, about $0.0152 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
opengeni AGENTS.md
Instructions for Cloudgeni-ai/opengeni, covering agent / automation notes (opengeni), full local stack, architecture notes, pull-request delivery across moving main and keeping these notes current.
hivekeep CLAUDE.md
Instructions for MarlBurroW/hivekeep, covering hivekeep, documentation map, tech stack, key conventions and naming.
useagent CLAUDE.md
Claude Code instructions for useagenthq/useagent, covering useagent - claude.md and hard rules.
agenteval copilot-instructions.md
Instructions for lukasmetzler/agenteval, covering copilot instructions, language, rules and suggestions.
agenteval backend.instructions.md
Instructions for lukasmetzler/agenteval, covering backend instructions, api design, database and performance.
agent-3md AGENTS.md
AGENTS.md instructions for CorvidLabs/agent-3md, covering agent-3md, project map, conventions and corvidlabs trust toolchain.