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/builddownai/skills/claude-mdgit clone --depth 1 https://github.com/BuildDownAI/skillsWrote 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/builddownai/skills/claude-md)<a href="https://agentmods.dev/instructions/builddownai/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/builddownai/skills/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 | $0.01026 | $0.01026 |
| Opus 5 | $0.00513 | $0.00513 |
| Sonnet 5 | $0.00205 | $0.00205 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade B, and why
skills CLAUDE.md scanned grade B 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 5d 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
- **MCP server:** `linear-eudoxus` — this repo's own project-scoped server (`.mcp.json`), endpoint `https://mcp.linear.app/mcp`, pre-approved in `.claude/settings.json`. Named per workspace (not a generic `linear-server` How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project configuration
This repo's skills (bd-build-up, bd-build-down, bd-summit-push, etc.) help a human plan work — decomposing
objectives into issues and driving them. They reference external services through {{PLACEHOLDER}}
tokens. This file binds those placeholders to the concrete tools for this project.
Issue tracker — Linear
- tracker.kind:
linear - MCP server:
linear-eudoxus— this repo's own project-scoped server (.mcp.json), endpointhttps://mcp.linear.app/mcp, pre-approved in.claude/settings.json. Named per workspace (not a genericlinear-server) so its OAuth token stays distinct from other Linear workspaces (e.g. acme) and they never steal each other's auth. Thebuilddownplugin bundles no MCP servers; this server is for developing the skills repo itself and is not shipped to plugin users. - Workspace:
eudoxus— bound at authentication time (run/mcpand authenticate thelinear-eudoxusserver; choose the Eudoxus workspace in the OAuth grant) - Team:
BDS— file/list/search issues against this team - Team URL: https://linear.app/eudoxus/team/BDS/overview
When a skill resolves {{TRACKER}}, it means the linear-eudoxus MCP, Eudoxus workspace, team BDS.
New issues and projects created by bd-build-up / bd-mega-build-up go into team BDS unless told otherwise.
AI-Implement label handoff — testing orchestrator
The skills don't run inside AI-Implement; they file issues that it later picks up. This binds that handoff.
{{IMPLEMENT_LABEL}}:AI-Implement(the label a finished issue gets so the orchestrator implements it)- Pickup target: AI-Implement testing instance (not production) — admin UI at
https://ai-implement-testing-orchestrator.fly.dev/admin#projects - Team it polls:
BDS— so labeled BDS issues are safe to experiment with; they do not touch the production AI-Implement backlog (team AI-Implement / AII-*). - Feature-branch grouping behaviour the skills must respect (parent/child feature nodes, child PRs into
ai-implement/feature/<key>, internal roll-ups vs the top-of-tree human-gate PR): seeplugin/skills/bd-shared/feature-branch-grouping.md.
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.
- 5d ago First seen · 65 lines · 1,026 tokens per session scan B 712ae45135ed
skills CLAUDE.md is an instructions file published in the GitHub repository BuildDownAI/skills (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 1,026 tokens to every session, about $0.0051 per session on Opus 5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
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.
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 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.