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 slack-notifygit 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/slack-notify)<a href="https://agentmods.dev/skills/runxhq/runx/slack-notify"><img src="https://agentmods.dev/badge/skills/runxhq/runx/slack-notify.svg" alt="Measured on agentmods" 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 33 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 | $0.00029 | $0.00833 |
| Opus 5 | $0.00015 | $0.00417 |
| Sonnet 5 | $0.00006 | $0.00167 |
| Haiku 4.5 | $0.00003 | $0.00083 |
Grade A, and why
slack-notify 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 4d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slack Notify
Send one deliberate Slack channel notification without exposing a Slack token to the skill or letting approved content drift before delivery. The skill separates safe message planning from the consequential provider mutation and requires Slack readback before it calls the notification delivered.
Use this for bounded notifications to a known workspace and channel. It is not a team inbox, a Slack history reader, or a customer-support workflow. Higher- level operator skills may prepare the message and destination, but this skill owns the final channel-post boundary.
Composes
send-as#plan
Runners
The default notify runner plans, requests approval only at the live post,
delivers once, and requires independent readback. plan validates a channel name, channel id, or exact
slack://workspace/channel destination, computes an inline message digest with
Runx's native data.digest, and binds that digest, the named principal, and the
send intent through the canonical send-as planning model. It does not post
and needs no approval. Delivery still requires the exact connector locator.
deliver accepts only that exact plan, the matching destination and message
text, and a stable UUID idempotency key. Runx recomputes the digest and compares
the complete delivery binding without echoing message content. It then:
- stops at explicit human approval;
- resolves the configured provider binding for
channel.postand the follow-upchannel.post.read; - asks the selected provider transport to execute that bounded mutation while its credential boundary retains custody; and
- reads the returned message locator back from Slack, compares the exact locator, destination, content digest, and occurrence time, then seals only those bounded evidence fields.
The binding may be local, self-hosted, third-party, or Runx-hosted. The skill never receives a Slack token, constructs a raw HTTP request, owns a tenant, or stores connector credentials in its inputs or receipts.
What ships with it
8 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/broadcast-held-for-approval.yaml 1.7 KB
- fixtures/default-notifies-and-verifies.yaml 2.9 KB
- fixtures/default-requires-live-delivery-binding.yaml 1.6 KB
- fixtures/deliver-reuses-notification-plan.yaml 2.6 KB
- fixtures/delivery-plan-drift.yaml 1.1 KB
- fixtures/needs-connector-and-fields.yaml 301 B
- slack-notify.mjs 4.4 KB runs code
- X.yaml 9.5 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.
- 4d ago First seen · 85 lines · 29 tokens per session scan A 50fcca88e86b
slack-notify is a skill published in the GitHub repository runxhq/runx (84 stars, last pushed yesterday), licensed Apache-2.0. It adds 29 tokens to every session and 833 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
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
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.