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 skills add thangnguyenworkspace/industry-pulse --skill research-crawl-emailgit clone --depth 1 https://github.com/thangnguyenworkspace/industry-pulseWrote 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/skills/thangnguyenworkspace/industry-pulse/research-crawl-email)<a href="https://agentmods.dev/skills/thangnguyenworkspace/industry-pulse/research-crawl-email"><img src="https://agentmods.dev/badge/skills/thangnguyenworkspace/industry-pulse/research-crawl-email/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/skills/thangnguyenworkspace/industry-pulse/research-crawl-email"><img src="https://agentmods.dev/badge/skills/thangnguyenworkspace/industry-pulse/research-crawl-email.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 | $0.00033 | $0.04719 |
| Opus 5 | $0.00016 | $0.02360 |
| Sonnet 5 | $0.00007 | $0.00944 |
| Haiku 4.5 | $0.00003 | $0.00472 |
Grade A, and why
research-crawl-email 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 11d 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 — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Crawl Email
Argument: $ARGUMENTS (required, see Runtime Inputs)
If $ARGUMENTS is empty or missing required fields, STOP and report which fields are absent.
Preamble
Runtime Inputs
Parse from $ARGUMENTS:
--senders=[EMAIL1,EMAIL2,...] [JSON-style array of exact RFC-5322 email addresses, non-empty; display names not supported. Singular invocation expressed as a single-element array.]
--raw-output-dir={PATH} [absolute path to a directory where per-sender rendered markdown files will be written]
# Optional power params (omit when not needed):
--days={N} [positive integer time window in days; default 1]
--max-per-sender={N} [per-sender message cap; default 10; truncates newest-first]
Validation rules (executed before §1.0):
--sendersand--raw-output-dirare mandatory. If either missing, STOP and report which is absent.--sendersmust parse as a JSON array of strings, non-empty. Reject otherwise (senders-malformed).- Each entry in
--sendersmust match RFC-5322 email shape (<local>@<host>with at least one.in host). First failing entry → STOP and report the offending value (senders-malformed). --raw-output-dirmust be absolute. Reject relative paths (callers own path resolution).--daysmust parse as positive integer when supplied; default 1.--max-per-sendermust parse as positive integer when supplied; default 10.
If any validation fails, STOP and report which field failed.
Global References
GMAIL_SEARCH_TOOL = mcp__claude_ai_Gmail__search_threads
GMAIL_GET_THREAD = mcp__claude_ai_Gmail__get_thread
The leaf composes these two MCP tools directly in the caller's context. Both require harness permission approval on first use per context, any caller may hit the prompt on its first invocation per session; surface which tool needs approval and re-invoke after the user grants it.
Caller Isolation
Pure primitive, no agent spawn, no pipeline agents, no telemetry. The skill runs the Gmail search + per-thread body fetch + render directly in the invoking context; the caller absorbs the Gmail thread context cost (full thread bodies land in the caller's window). Callers crawling many senders, or composing this leaf alongside other work, wrap the invocation in their own isolation:
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.
- 11d ago First seen · 380 lines · 33 tokens per session scan A 57eea4d1b6f4
research-crawl-email is a skill published in the GitHub repository thangnguyenworkspace/industry-pulse (4 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 4,719 once invoked, about $0.0002 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 skills, from other repositories
competitor-x-ray
Decode any set of competitors into their ICP (ideal customer profile), their funnel (how a stranger becomes a customer), and their monetization (every revenue stream and price point). Researches each competitor against real sources and synthesizes a cross-competitor comparison. Use whenever the user wants to research…
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…