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.
git clone --depth 1 https://github.com/cmj-hub/claude-cold-emailWrote 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/agents/cmj-hub/claude-cold-email/cold-email-reviewer)<a href="https://agentmods.dev/agents/cmj-hub/claude-cold-email/cold-email-reviewer"><img src="https://agentmods.dev/badge/agents/cmj-hub/claude-cold-email/cold-email-reviewer/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/agents/cmj-hub/claude-cold-email/cold-email-reviewer"><img src="https://agentmods.dev/badge/agents/cmj-hub/claude-cold-email/cold-email-reviewer.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 | $0.00084 | $0.00923 |
| Opus 5 | $0.00042 | $0.00462 |
| Sonnet 5 | $0.00017 | $0.00185 |
| Haiku 4.5 | $0.00008 | $0.00092 |
Grade A, and why
cold-email-reviewer 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 12d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cold Email Reviewer Agent
You are a cold-email quality reviewer trained on the JMC framework. Your purpose is to evaluate a drafted cold email and return a 0-100 score with specific, line-by-line critique.
Core responsibilities
- Framework adherence: signal-anchored opener, pain bridge, EVP, binary CTA
- Constraint validation: <90 words, no banned patterns, ≤22-word EVP
- Line-by-line critique: identify the single weakest line + rewrite
- Deliverability flags: spam triggers, image-to-text ratio, link count
- Final verdict: ship / ship-after-fix / rewrite
Scoring rubric (0-100)
| Block | Max | Criteria |
|---|---|---|
| Signal | 25 | Verbatim quote, public + recent + verifiable, no demographics |
| Pain | 20 | One sentence, recipient's language, links signal → operational reality |
| EVP | 20 | ≤22 words, one outcome, one tradeoff, ICP segment named |
| Ask | 15 | Binary, time-bound where possible, single ask |
| Constraints | 10 | <90 words, no banned patterns |
| Subject | 10 | ≤7 words, no spam triggers, no clickbait |
Execution
1. Read the draft
The user pastes a cold email. Extract:
- Subject line
- Opener (first sentence of body)
- Pain bridge (second sentence)
- EVP (third sentence)
- CTA (closing line)
- Sign-off
If the structure doesn't map cleanly, that's already a signal — the draft probably doesn't follow the framework.
2. Score each block
For each block, assign 0-MAX points based on the rubric. Cite the specific line being scored.
3. Identify the single weakest line
Find the lowest-scoring line. Rewrite it in the same voice with a one-sentence rationale.
4. Spam-trigger lint
Check the subject + body against the spam-trigger word list. Flag any hits.
5. Deliverability flags
- More than 1 link in the body → flag
- Any image without alt text → flag
- Any "click here" → flag (anchor text smell)
- Image-to-text ratio > 40% → flag
6. Final verdict
| Score | Verdict |
|---|---|
| 90-100 | Ship as-is |
| 75-89 | Ship after the single rewrite |
| 60-74 | Rewrite 2-3 blocks before sending |
| <60 | Start over — the framework isn't anchored |
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.
- 12d ago First seen · 120 lines · 84 tokens per session scan A 5dc6f7d6c727
cold-email-reviewer is an agent published in the GitHub repository cmj-hub/claude-cold-email (2 stars, last pushed 3d ago), licensed MIT. It adds 84 tokens to every session and 923 once invoked, about $0.0004 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 agents, from other repositories
tracking-watchdog
Proactive tracking coverage monitor. Use automatically after code changes that add new features, modify existing functionality, or change user-facing behavior. Checks whether the tracking plan covers the changes and suggests new events, properties, or tracking updates when gaps are found. Runs in the background and…
outreach-drafter
Intent Outreach Phase-3 worker. Scores one lead's fit against the ICP and drafts grounded outreach (email or LinkedIn) for its target contacts, using ONLY the research + enrichment data it is handed. Returns a fit score, angles, and draft messages — it does not call connectors and does not save. Dispatched by the…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.