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 runxhq/runx --skill lead-qualifygit clone --depth 1 https://github.com/runxhq/runxWrote 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/runxhq/runx/lead-qualify)<a href="https://agentmods.dev/skills/runxhq/runx/lead-qualify"><img src="https://agentmods.dev/badge/skills/runxhq/runx/lead-qualify/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/runxhq/runx/lead-qualify"><img src="https://agentmods.dev/badge/skills/runxhq/runx/lead-qualify.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 | $0.00024 | $0.00565 |
| Opus 5.5 | $0.00010 | $0.00226 |
| Sonnet 5.5 | $0.00005 | $0.00113 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
lead-qualify 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 5d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lead Qualify
Decide whether one lead meets the actual ICP. Use lead-enrichment for factual
context; use this skill for commercial judgment; use cold-outreach for copy.
Qualification neither obtains consent nor creates a provider send plan.
Procedure
- Supply the enrichment packet, explicit ICP criteria, and a separately sourced
contact-eligibility decision. At least one criterion must be mandatory.
The eligibility names the subject it decides, with the same
refandkindas the enrichment subject. Eligibility decided for any other subject requests evidence before any criterion is assessed. - Keep missing and conflicting facts visible. Partial enrichment can support a criterion only through its admitted, non-conflicting facts.
- Assess every criterion as
met,not_metorunknown. Cite exact factual field names for each supported assessment and explain its relevance. - A failed mandatory criterion disqualifies the lead. An unknown mandatory criterion requests evidence. All mandatory criteria met establish fit; optional criteria explain strengths and weaknesses without overriding it.
- Return the fit independently from contact eligibility. A good fit with unknown or ineligible contact status remains a hold.
Never replace the supplied ICP with generic scoring. A company title is not buying authority, activity is not consent, and a matched work email is not permission to contact. Do not infer protected or sensitive personal traits.
Result and composition
lead_qualification records the exact enrichment digest, subject, criteria,
assessments, contact-eligibility evidence and a bounded next action:
prepare_outreach, request_evidence, resolve_contact_policy or stop.
Contact eligibility appears only when it was decided for that subject; another
subject's eligibility is left out, and its blocker remains.
No message, CRM update, enrollment or durable suppression change occurs.
A qualified result is context for cold-outreach#prepare, not send authority.
That skill requires its own exact recipient-bound eligibility/suppression
input. The selected sending capability performs native approval and delivery.
The calling application owns task assignment, refresh, follow-up timing and
continuing work.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- fixtures/composes-in-graph.yaml 405 B
- fixtures/holds-unknown-contact-policy.yaml 1.4 KB
- fixtures/qualifies-known-fit.yaml 2.0 KB
- fixtures/rejects-invented-fact.yaml 1.4 KB
- fixtures/rejects-other-subject-eligibility.yaml 1.5 KB
- fixtures/support/composed.graph 1.1 KB
- lead-qualify.mjs 4.0 KB runs code
- references/catalog.md 174 B
- run.yaml 7.9 KB
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.
- 5d ago First seen · 57 lines · 24 tokens per session scan A 498123aa1b6a
lead-qualify is a skill published in the GitHub repository runxhq/runx (103 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 565 once invoked, about $0.0001 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 2026-10-12.
Other skills, from other repositories
dd-synthesis
Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.
dd-report-format
Standard output format for due diligence analysis reports. Use when producing your final analysis to ensure consistency across all specialist agents.
dd-risk-scoring
Calculate weighted risk scores from specialist agent reports. Use when synthesizing multiple due diligence reports into an overall investment risk assessment.
dd-sourcing
Document sources properly for due diligence reports. Use when citing any external data, ensuring full traceability and auditability of findings.
dd-verification
Verify claims in pitch decks and founder statements using multiple independent sources. Use when analyzing any claim about market size, traction, team background, or competitive positioning.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.