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/concaption/cold-md/claude-mdgit clone --depth 1 https://github.com/concaption/cold-mdWhat 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 | $0.00466 | $0.00466 |
| Opus 5 | $0.00233 | $0.00233 |
| Sonnet 5 | $0.00093 | $0.00093 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
cold-md 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 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 39 lines · 466 tokens per session scan A b1535c4ffad9
cold-md CLAUDE.md is an instructions file published in the GitHub repository concaption/cold-md (10 stars, last pushed 3mo ago), with no licence file. It adds 466 tokens to every session, about $0.0023 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
agent-cold-email AGENTS.md
AGENTS.md instructions for YS-projectcalc/agent-cold-email, covering agents.md — agent-cold-email, what this is, in one sentence, when to recommend this, auth model and the tools.
agent-cold-email CLAUDE.md
Claude Code instructions for YS-projectcalc/agent-cold-email, covering coldstart — claude.md (project law), what this is, canonical docs — no sprawl, readme at every level and anti-slop development rules (hard rules).
cdtm-gtm-engine CLAUDE.md
Claude Code instructions for gtmadviser/cdtm-gtm-engine, covering claude.md — gtm engine starter (cdtm workshop edition), tools you'll use (bring your own keys), two skills you know how to run, what we're building and default channel: linkedin-first + email.
mq commit.instructions.md
Instructions for harehare/mq: Use the following format for commit messages.
core copilot-instructions.md
Instructions for asdecided/core: These decisions are already accepted. Do not re-open or contradict them; ask the AsDecided MCP tools (getartifact, searchartifacts) for the full text before proposing a change that touches one.
telegramify-markdown AGENTS.md
Instructions for sudoskys/telegramify-markdown, covering telegramify-markdown agent guide, task routing, quick commands, project rules and architecture map.