Borrowing it
Nothing to install: this file belongs to bierlingm/spikes. 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/bierlingm/spikes/main/CLAUDE.mdgit clone --depth 1 https://github.com/bierlingm/spikesWrote 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/bierlingm/spikes/claude-md)<a href="https://agentmods.dev/instructions/bierlingm/spikes/claude-md"><img src="https://agentmods.dev/badge/instructions/bierlingm/spikes/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/bierlingm/spikes/claude-md"><img src="https://agentmods.dev/badge/instructions/bierlingm/spikes/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00359 | $0.00359 |
| Opus 5.5 | $0.00144 | $0.00144 |
| Sonnet 5.5 | $0.00072 | $0.00072 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
spikes 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 1mo 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.
What it actually says
Spikes — Claude Code Context
Read AGENTS.md for full project details, architecture, and patterns.
First thing every session
werk tree # See what's in play
werk list # Active tensions (there is no `werk survey` subcommand)
All work tracking lives in werk. Update tensions as you go — werk reality <id>, werk note add <id>, werk resolve <id>. If werk tree reports no tensions (true as of 2026-09-16: no .werk/ workspace exists in this repo), track work as GitHub issues in bierlingm/spikes and bierlingm/spikes-hosted instead.
Quick reference
- What: Feedback tool for AI-assisted building. Click elements, rate them, get JSON with CSS selectors.
- Stack: Rust CLI + vanilla JS widget + Cloudflare Workers/D1/R2 + Stripe
- Domain: spikes.sh
- CLI version: 0.5.0
- Root goal: 10 paying users
- Tests:
cd cli && cargo test/cd ../spikes-hosted/worker && npm test - Widget Tests:
cd tests/widget && npm test/npx agent-ci run --workflow workflows-local/widget.yml - Agent-CI:
npx agent-ci run --workflow workflows-local/test.yml(local only) - Deploy: push to main (site) or tag v* (binaries)
Note: GitHub Actions runs test.yml (CLI tests), deploy.yml (site) and release.yml (binaries on v* tags); workflows-local/test.yml is the local agent-ci equivalent.
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.
- 1mo ago Changed · +71 tokens per session b879a03d4d9b
- 2mo ago First seen · 27 lines · 288 tokens per session scan A ce008658f82a
spikes CLAUDE.md is an instructions file published in the GitHub repository bierlingm/spikes (1 stars, last pushed 21d ago), licensed MIT. It adds 359 tokens to every session, about $0.0014 per session on Opus 5.5. 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.
spikes CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| spikes CLAUDE.mdbierlingm/spikes | Instructions file | 1 | 21d ago | MIT | A | 359 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |