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/cubenest/rrweb-stack/claude-mdgit clone --depth 1 https://github.com/Cubenest/rrweb-stackWhat 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 | $0.00765 | $0.00765 |
| Opus 5 | $0.00382 | $0.00382 |
| Sonnet 5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade C, and why
rrweb-stack CLAUDE.md scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- The canonical agent-instruction doc for this repo is AGENTS.md — edit there, not here. This file exists only because Claude Code reads CLAUDE.md (not AGENTS.md); the import below loads the same context so both surfa How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@AGENTS.md
Claude Code
Deploying the docs sites
Both Astro docs sites (apps/peek-docs → peek.cubenest.in,
apps/tracelane-docs → tracelane.cubenest.in) are deployed to Vercel via CLI.
Deploy from the monorepo root — deploying from the app subdirectory only
uploads that directory and leaves workspace deps (@cubenest/docs-shared,
@peekdev/todomvc-demo) unresolvable on Vercel's build server.
Procedure:
-
Create a temporary
vercel.jsonat the repo root (gitignored):// peek-docs { "installCommand": "pnpm install --frozen-lockfile", "buildCommand": "pnpm --filter peek-docs... run build", "outputDirectory": "apps/peek-docs/dist" } -
Deploy with the project's env vars:
VERCEL_PROJECT_ID=prj_wbLWp8utBFQXFpIxNC10i5ty5DNo \ VERCEL_ORG_ID=team_ZKvGQO7dXxGBLl1iJ4vXWwnD \ vercel --prod -
Swap
vercel.jsonfor tracelane-docs and repeat:{ "installCommand": "pnpm install --frozen-lockfile", "buildCommand": "pnpm --filter tracelane-docs... run build", "outputDirectory": "apps/tracelane-docs/dist" }VERCEL_PROJECT_ID=prj_4Lnsk0ODEw2gXUzPPpiz1an8gqzt \ VERCEL_ORG_ID=team_ZKvGQO7dXxGBLl1iJ4vXWwnD \ vercel --prod -
Delete
vercel.jsonand.vercel/from the repo root when done.
Why: the cd ../.. && pnpm install install command in each app's
.vercel/project.json was designed for Vercel Git integration (which clones
the full repo). CLI deploys from a subdirectory upload only that directory,
so the monorepo root is unreachable. Deploying from the root with
VERCEL_PROJECT_ID uploads everything (≈15 MB) and pnpm --filter runs the
build with correct PATH for cross-env and astro.
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 · 73 lines · 765 tokens per session scan C 32963fbc3994
rrweb-stack CLAUDE.md is an instructions file published in the GitHub repository Cubenest/rrweb-stack (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 765 tokens to every session, about $0.0038 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
qaskills AGENTS.md
Instructions for PramodDutta/qaskills, covering agents.md, project overview, common commands, run a single package and run tests in watch mode.
toki AGENTS.md
Instructions for choi138/toki, covering workspace rules, source of truth, toki workflow, required checks and global safety rules.
Ocul-PM CLAUDE.md
Instructions for bunhine0452/Ocul-PM, covering claude.md, what this is, commands, single frontend test and rust (run from src-tauri/).
gomaa AGENTS.md
Instructions for M4F-S/gomaa, covering 🧠 gomaa autonomous agent ecosystem & vps operations guide, 🌐 production vps infrastructure, 🤖 the 5-agent hermes fleet (per-agent memory databases), ⚡ quick operations cli (./scripts/vps.sh) and 2. run runtime mcp health audit across all agents.
sample-well-architected-skills-and-steering copilot-instructions.md
Copilot instructions for aws-samples/sample-well-architected-skills-and-steering, covering well-architected framework, role, when to apply, pillars and design principles.
qaskills CLAUDE.md
Instructions for PramodDutta/qaskills, covering claude.md, what this is, conventions (non-negotiable), commands and single package.