Borrowing it
Nothing to install: this file belongs to calven-ai/demoverse. 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/calven-ai/demoverse/main/CLAUDE.mdgit clone --depth 1 https://github.com/calven-ai/demoverseWrote 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/calven-ai/demoverse/claude-md)<a href="https://agentmods.dev/instructions/calven-ai/demoverse/claude-md"><img src="https://agentmods.dev/badge/instructions/calven-ai/demoverse/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 | $0.00528 | $0.00528 |
| Opus 5 | $0.00264 | $0.00264 |
| Sonnet 5 | $0.00106 | $0.00106 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
demoverse 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 8d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md: Claude Code operating notes for Demoverse
@AGENTS.md
The engine contract, the onboarding playbook, and the fill rules all live in
AGENTS.md (imported above). This file adds only what is
Claude-Code-specific.
Skills
| Skill | What it runs |
|---|---|
/setup |
The onboarding playbook (AGENTS.md Part 2): interview → config → init → first increment → optional connectors |
/pipeline-update [weeks] |
The routine weekly increment, end to end: advance → fill via opp-filler subagents → ingest → lint → fix → reconcile → commit |
/backfill-opps [N] |
The detail-layer loop for N opportunities: plant → fill (one subagent per opp) → ingest → lint → fix → reconcile → commit per opp |
/import-hubspot |
The deterministic HubSpot import: provision the schema → import the CRM structure into the dedicated test account → verify record-by-record |
Subagent strategy (critical for context health)
Never write result-file prose inline in the main context. Every fill goes
through the opp-filler subagent (.claude/agents/opp-filler.md, Read/
Write/Glob only), one subagent per opportunity, never batched. The main
context only runs shell commands (apply, lint, git) and dispatches
subagents. If a subagent hits a session limit, re-launch it for the remaining
artifacts of that same deal only.
All apply/lint/git commands stay serial in the main context.
state/world.json is written whole, last-writer-wins. Fills parallelize
freely (distinct result files).
Overnight backfill
For a bulk detail-layer backfill, run the skill as a self-paced loop:
/loop /backfill-opps 5. Each iteration is independently resumable, thanks to
idempotent planting, planned-only ingest, upsert reconcile and per-opp commits.
Stop when npm run apply -- --next=1 prints
(no opportunities need a detail layer).
Session hygiene
- Past ~150k context, suggest wrapping up and continuing fresh (or
/compactat a natural boundary). - Keep tool output small: pipe long logs through
tail/grep. - Read each request prompt once; don't re-read files already in context.
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.
- 8d ago First seen · 45 lines · 528 tokens per session scan A 095eb2602a43
demoverse CLAUDE.md is an instructions file published in the GitHub repository calven-ai/demoverse (2 stars, last pushed 4d ago), licensed MIT. It adds 528 tokens to every session, about $0.0026 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.