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/bierlingm/spikes/agents-mdgit clone --depth 1 https://github.com/bierlingm/spikesWhat 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 | $0.01621 | $0.01621 |
| Opus 5 | $0.00811 | $0.00811 |
| Sonnet 5 | $0.00324 | $0.00324 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade A, and why
spikes 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 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.
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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<coding_guidelines>
Spikes — Agent Instructions
Project Overview
Spikes is the feedback loop tool for AI-assisted building. Building prototypes is easy now (Claude Code, Cursor, v0). The bottleneck is turning feedback into action. Spikes makes feedback structured, precise, and agent-ready.
Two core use cases:
- You reviewing agent work — Click elements, leave comments, agent gets exact CSS selectors
- Collecting feedback from others — Share a link, they spike it, you get JSON for your agent
Components:
- Widget: Vanilla JS (
widget/spikes.js, ~14KB gzipped, zero dependencies) - CLI: Rust binary (
cli/, v0.4.0, 30 subcommands) - MCP Server: 9 tools via
spikes mcp serve(stdio or HTTP transport) - Site: Landing page and docs (
site/, deployed to Cloudflare Pages) - Worker: Cloudflare Workers backend (D1 + R2)
- NPM:
spikes-mcppackage for zero-install MCP
Work Tracking with werk
This project uses werk for all task/tension tracking. Always check werk before starting work.
werk tree # See full tension tree
werk survey # Field survey — tensions by urgency
werk show <id> # Tension details + history
werk list # List all active tensions
werk reality <id> "new..." # Update current reality
werk note add <id> "text" # Add observational note
werk resolve <id> # Mark tension resolved
werk add "desired" "actual" --parent <id> # Create child tension
The root tension is #1: "Have 10 paying users on spikes.sh". All work should relate to this goal or its children.
Architecture
widget/
spikes.js # Drop-in widget (14KB gzipped, IIFE pattern)
cli/
Cargo.toml
src/
main.rs # 30 subcommands via clap
commands/ # list, show, export, inject, serve, mcp, login, share, billing, etc.
spike.rs # Spike data structure
storage.rs # JSONL persistence (.spikes/feedback.jsonl)
auth.rs # Token/API key management
config.rs # TOML config (.spikes/config.toml)
output.rs # JSON/table formatting
error.rs # Error types
templates/
cloudflare/ # Self-host scaffold (Worker + D1 + R2)
site/
index.html # Landing page
docs.html # Documentation
agents.md # Machine-readable agent discovery
llms.txt # LLM context index
spikes.js # Widget served from spikes.sh
packages/
spikes-mcp/ # NPM package for zero-install MCP (npx spikes-mcp)
action/ # GitHub Action for CI gating on feedback
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 · 163 lines · 1,621 tokens per session scan A 89ad982c8b06
spikes AGENTS.md is an instructions file published in the GitHub repository bierlingm/spikes (1 stars, last pushed 1mo ago), licensed MIT. It adds 1,621 tokens to every session, about $0.0081 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
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.
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.