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 list-hygiene-judgegit 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/list-hygiene-judge)<a href="https://agentmods.dev/skills/runxhq/runx/list-hygiene-judge"><img src="https://agentmods.dev/badge/skills/runxhq/runx/list-hygiene-judge/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/list-hygiene-judge"><img src="https://agentmods.dev/badge/skills/runxhq/runx/list-hygiene-judge.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 | $0.00029 | $0.00875 |
| Opus 5.5 | $0.00012 | $0.00350 |
| Sonnet 5.5 | $0.00006 | $0.00175 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
list-hygiene-judge 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 yesterday.
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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
List Hygiene Judge
Use this skill after collecting current contact evidence and before preparing a campaign. It decides whether a contact remains eligible, needs re-permission, must be suppressed, or needs human review. When policy justifies a state transition, it records that decision in the operator's consent ledger with optimistic concurrency and verifies the exact event through a second read.
This skill never sends a message and never mutates a mailing provider. A later
message-send run must read the current consent state again at delivery time. The
ledger records the operator's policy decision; it does not replace provider
unsubscribe or bounce data.
Operating model
The caller supplies one bounded engagement observation, the current consent
observation, and the policy threshold that applies to the contact. The evidence
must be marked read and versioned to the same ledger head that the runner
reads through the store's projection.read. Missing, stale, ambiguous, or conflicting
evidence produces human_review without a write.
The deterministic decision order is conservative:
- An unsubscribe marker stops automation.
- An existing suppression is preserved; age alone can never relax it.
- Verified hard-bounce evidence suppresses when policy permits that automatic action, otherwise it stops for review.
- A subscribed contact whose last engagement exceeds the decay threshold is
moved to
re_permission. - A clean, recent subscribed contact returns
verifywithout writing.
Only re_permission and suppress can create transitions. The append uses the
observed ledger version and the caller's stable idempotency key. Readback must
match the append status, source identity, new version, event reference, event
digest, and projection digest before the result reports a recorded transition.
No-write decisions also perform a second read and require the projection to
remain unchanged.
Authority and finality
The runner requests runx:data:read and, only for an admitted transition,
runx:data:append. These scopes authorize a bounded consent-ledger operation;
they do not authorize delivery or changes to a CRM or mailing provider. The
data-source binding owns storage and credentials.
What ships with it
5 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.
- yesterday Changed · -7 lines d05e078fa291
- 5d ago Changed · +7 lines 31d6542ecd5c
- 1mo ago First seen · 90 lines · 29 tokens per session scan A ed5f754acec3
list-hygiene-judge is a skill published in the GitHub repository runxhq/runx (103 stars, last pushed today), licensed Apache-2.0. It adds 29 tokens to every session and 875 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 2026-09-15.
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.
rule6-rights-gate
Hard Rule 6 pre-publication rights gate — check licensing/provenance AND likeness/voice consent over a generated or third-party media asset before publish/use, and emit the machine-readable gate record. Use at the S4 Verify step of content/image, content/video, content/audio-assets (or any asset headed for…