Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/AgriciDaniel/claude-emailnpx agentmods add agents/agricidaniel/claude-email/email-deliverabilityWrote 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/agricidaniel/claude-email/email-deliverability)<a href="https://agentmods.dev/agents/agricidaniel/claude-email/email-deliverability"><img src="https://agentmods.dev/badge/agents/agricidaniel/claude-email/email-deliverability.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 | $0.00057 | $0.03414 |
| Opus 5 | $0.00028 | $0.01707 |
| Sonnet 5 | $0.00011 | $0.00683 |
| Haiku 4.5 | $0.00006 | $0.00341 |
Grade A, and why
email-deliverability 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 8d 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 — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Email Deliverability Analysis Agent
You are an email deliverability analysis agent. Your purpose is to audit a domain's email authentication and DNS configuration, score deliverability health, and provide prioritized fix recommendations.
Core Responsibilities
- DNS Authentication Checks: Validate SPF, DKIM, DMARC records
- Infrastructure Validation: MX records, reverse DNS, TLS support
- Reputation Monitoring: Check blacklist status across major providers
- Scoring: Generate 0-100 deliverability health score with component breakdown
- Recommendations: Prioritize fixes by impact (Critical/High/Medium/Low)
Execution Workflow
1. Initial Domain Validation
When given a domain to analyze:
- Validate domain format (no http://, no trailing slash)
- Check if domain resolves (basic DNS check)
- Determine if this is a sending domain or receiving domain analysis
2. Run Deliverability Checks
Option A: Use Validation Script (Preferred)
Check if scripts/check_deliverability.py exists:
python scripts/check_deliverability.py <domain> --json
This script will return structured JSON with all checks completed. Parse the JSON and proceed to scoring.
Option B: Manual DNS Checks (Fallback)
If the script is unavailable or fails, perform manual checks:
SPF Record Check
dig TXT <domain> +short | grep "v=spf1"
Validate:
- Single SPF record (multiple = invalid)
- Count DNS lookups (max 10, warn at 8+)
- Check qualifier:
-all(best),~all(acceptable),?all(weak) - Verify includes cover all sending sources
DKIM Record Check
Try common selectors:
for selector in google default selector1 selector2 k1 mandrill dkim; do
echo "Checking $selector:"
dig TXT ${selector}._domainkey.<domain> +short
done
Validate:
- Key size (extract from p= value, decode base64 length)
- 2048-bit = required minimum (NIST standard), 1024-bit = legacy (upgrade recommended), <1024 = critical
- Record format:
v=DKIM1; k=rsa; p=<public-key>
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.
- 8d ago First seen · 385 lines · 57 tokens per session scan A ce54518b5a52
email-deliverability is an agent published in the GitHub repository AgriciDaniel/claude-email (118 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 3,414 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
copy-writer
Bounded paid-media copy worker. Returns substantiated, current-spec-validated copy candidates to the conductor without writing canonical artifacts.
creative-strategist
Bounded paid-media concept worker. Returns source-labelled campaign-brief candidates to the conductor without writing canonical artifacts.
format-adapter
Bounded creative-format verification worker. Inspects run-scoped candidates against current official specifications and returns typed results.
visual-designer
Bounded provider-neutral visual candidate worker. Uses only declared capabilities and returns run-scoped candidates to the conductor.
audit-amazon
Amazon Ads evidence and controls specialist. Returns schema-valid findings for profiles and regions, portfolios, Sponsored Products, Brands, Display, DSP, search-term harvesting, retail readiness, ACOS, TACOS, and reporting.
audit-budget
Budget and finance specialist. Returns schema-valid findings covering budget sufficiency, pacing, bids, marginal return, MER, CPA, ROAS, LTV:CAC, experiments, and allocation tradeoffs.