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-routergit 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-router)<a href="https://agentmods.dev/skills/runxhq/runx/lead-router"><img src="https://agentmods.dev/badge/skills/runxhq/runx/lead-router/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-router"><img src="https://agentmods.dev/badge/skills/runxhq/runx/lead-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 28 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00027 | $0.00821 |
| Opus 5 | $0.00014 | $0.00411 |
| Sonnet 5 | $0.00005 | $0.00164 |
| Haiku 4.5 | $0.00003 | $0.00082 |
Grade A, and why
lead-router 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 7d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lead Router
Not every lead should receive the same treatment. lead-router takes one
validated enrichment packet and chooses exactly one governed posture:
reach_out, nurture, or hold. The route and its evidence remain visible in
the receipt, so the decision is reviewable instead of disappearing inside an
ad-hoc prompt.
This is a routing and planning skill. It does not send a message, enroll a
campaign, or mutate a CRM. Reach-out and nurture outcomes prepare the exact
input for the canonical send-as planning boundary. A hold is recorded in the
Runx receipt only; it is not an external suppression-list update.
When to use it
Use lead-router after lead-enrichment has produced a validated packet and a
team needs one consistent qualify-then-plan decision. Use a campaign or
provider-specific skill directly when the audience and authorization are
already decided and no lead-level routing remains.
Never use it to bypass consent, contact a suppressed lead, or draft bespoke copy from raw signals. Enrichment owns evidence synthesis; content skills own copy; provider adapters own delivery.
How it works
- Runx digests and admits the enrichment packet, preserving its signal references and validation state.
- Consent and suppression outrank model judgment. A do-not-contact packet takes
the deterministic
holdpath. - For a ready packet, bounded judgment selects
reach_out,nurture, orholdand cites admitted signal references in the rationale. - Finalization produces either a deterministic hold or an exact, non-executed
send-ashandoff markedprepared_for_send_planning. - The later send lane performs content preflight, obtains any required approval, binds idempotency, invokes the provider, and verifies readback.
Ambiguity should become a hold, not an optimistic send plan. A hold is a clean, auditable terminal state rather than a workflow failure.
Inputs and result
enrichment_packetis validatedrunx.growth.lead_enrichment.v1data.principalnames the proposed downstream sender; it is not itself send authority.objectivedescribes the intended follow-up.provider_contextmay narrow a future provider binding but cannot authorize delivery.
What ships with it
4 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.
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.
- 7d ago First seen · 89 lines · 27 tokens per session scan A f875a05d9e79
lead-router is a skill published in the GitHub repository runxhq/runx (84 stars, last pushed 2d ago), licensed Apache-2.0. It adds 27 tokens to every session and 821 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
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-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-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.