Borrowing it
Nothing to install: this file belongs to anthonysuherli/br8n. 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/anthonysuherli/br8n/main/CLAUDE.mdgit clone --depth 1 https://github.com/anthonysuherli/br8nWrote 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/anthonysuherli/br8n/claude-md)<a href="https://agentmods.dev/instructions/anthonysuherli/br8n/claude-md"><img src="https://agentmods.dev/badge/instructions/anthonysuherli/br8n/claude-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 5.1 | $0.06408 | $0.06408 |
| Opus 5 | $0.03204 | $0.03204 |
| Sonnet 5 | $0.01282 | $0.01282 |
| Haiku 4.5 | $0.00641 | $0.00641 |
Grade A, and why
br8n CLAUDE.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 7d 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 — 383 lines — stays where its author put it; the contents beside it link to each section on GitHub.
br8n
Context-capture and resume engine — cuts the context-rebuild tax after an interruption by capturing developer intent and replaying it as a 30-second resume card.
On the "9.5 minutes" figure: it appears in the README, the site hero, and
skills/pickup/SKILL.md, but nothing in this repo sources it — docs/launch/ws6
concedes it "is an assumption." The sourced numbers are ~23 minutes to refocus after
an interruption (Gloria Mark, UC Irvine) and up to 45 for complex code. ws1 sets the
rule: cite the 23-minute figure, don't invent ROI claims. Fix or source the 9.5 before
using it in launch copy.
Design philosophy
Non-blocking by default. br8n must never hijack the user's turn to do its own work. The user's flow is sacred; br8n's work happens around it. Every feature that isn't a direct response to a user command should be built to this principle:
- Work in the background. Context collection (seeding, enrichment, distillation,
graph population) runs as background agents —
Agent(run_in_background)for orchestrated multi-step work, fire-and-forget hooks for cheap structural passes. Prefer agent teams (parallel subagents, each owning one slice — repo crawl, git history, web enrichment, schema drafting) over one long serial pass, so the wall-clock cost is the slowest slice, not the sum. Precedents: the activity-KG fire-and-forget population on capture (api/capture.py), the first-run-init background subagent (docs/plans/2026-06-01-br8n-first-run-init-design.md). - Gate decisions at turn boundaries, never mid-flow. Anything that genuinely needs the user — schema creation / KG ontology co-design, creating a new KB, a destructive or expensive choice — waits until the background work is ready, then surfaces a single one-line offer at the next turn boundary ("Schema draft is ready — set it up?"). Never a modal mid-edit, never a blocking prompt the user didn't ask for. The user opts in to the interactive step; until they do, br8n stays quiet and keeps working.
- Best-effort, fails silent. Background work never breaks the user's session. A failed seed, an unreachable backend, a graph error — all degrade to "do nothing visible" and fall through to an on-demand recovery path. Fail closed, stay invisible.
- Offer once, then go quiet. A gated offer that's declined or ignored is not re-raised every launch; stamp it and move on (the capability stays available on demand). Don't nag.
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.
- 7d ago First seen · 383 lines · 6,408 tokens per session scan A a257ab72e104
br8n CLAUDE.md is an instructions file published in the GitHub repository anthonysuherli/br8n (1 stars, last pushed 1mo ago), licensed MIT. It adds 6,408 tokens to every session, about $0.0320 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
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).
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.
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.