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 agentmods add skills/webhook-co/webhook/support-triagenpx skills add webhook-co/webhook --skill support-triagegit clone --depth 1 https://github.com/webhook-co/webhookWhat 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 | $0.00044 | $0.00421 |
| Opus 5 | $0.00022 | $0.00211 |
| Sonnet 5 | $0.00009 | $0.00084 |
| Haiku 4.5 | $0.00004 | $0.00042 |
Grade A, and why
support-triage 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 2d 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.
What it actually says
Support triage
Turn a vague technical report into a precise, reproducible, routable finding. Technical triage only.
Triage flow
- Restate the problem in one line: which surface (CLI/API/web/MCP), which capability (receive / inspect / replay / deliver), and the observed vs expected behavior.
- Reproduce with the smallest case: endpoint setup, a sample (redacted) event, the exact command/request. Note environment and version.
- Localize using OpenTelemetry traces and logs — follow the event id through ingest → DO → delivery. Check dedup/idempotency, retry/backoff state, and signature verification.
- Classify: bug vs misuse vs expected behavior; severity (data-loss/security > delivery failure > cosmetic); and the owning area (engine, a surface, infra, docs).
- Write the finding: summary, repro steps, expected vs actual, evidence (trace/log refs), suspected cause, and a suggested owner. Add a regression-test idea for any real bug.
Handling data safely
- Redact PII/PHI before quoting payloads/logs in any report. Never paste secrets, tokens, or full bodies.
- Reference events by id, not by contents.
Guardrails
- Stay technical and public-safe: no customer identities, no pricing/billing internals, no business strategy in write-ups.
- If the issue looks like a security problem (authz bypass, SSRF, secret/PII leak), escalate to a security review rather than patching ad hoc.
Progressive disclosure
Keep deep-dive playbooks (delivery-failure decision tree, signature-mismatch checklist) in
references/.
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.
- 2d ago First seen · 40 lines · 44 tokens per session scan A d3960509f810
support-triage is a skill published in the GitHub repository webhook-co/webhook (0 stars, last pushed 7d ago), licensed Apache-2.0. It adds 44 tokens to every session and 421 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
frontend-design-saas
S-tier SaaS dashboard and product UI reference. Use this skill when building application shells, data tables, settings panels, billing pages, dashboards, auth flows, admin tools, or any internal/customer-facing SaaS product UI. Inspired by Stripe, Linear, Vercel, Airbnb, Notion. Covers neutral-led design tokens…
prepare-cloudflare-production-deployment
Source-of-truth runbook for preparing this Vinext Cloudflare Workers SaaS template for production deployment. Use when setting up or auditing Cloudflare MCP resources, wrangler.jsonc bindings, Worker secrets, Turnstile, Email Sending, GitHub Actions secrets/variables, or GitHub CLI deployment wiring for this…
update-saasmail
Sync the local saasmail repo with the latest upstream changes from https://github.com/choyiny/saasmail. Use this skill whenever the user wants to update saasmail, pull upstream changes, sync with upstream, rebase on upstream, get the latest saasmail, or says "/update-saasmail". Handles adding the upstream remote if…
add-provider
Add a new storage or service provider to the core package. Use when implementing a new backend for StorageService (e.g., a new database) or a new service provider (e.g., a new LLM backend).
story-html-publisher
Final step of the AI Storybook pipeline. Consolidates the scenes, images, and per-scene audio into ONE self-contained HTML storybook — a swipe/tap player with every image and audio clip embedded as base64 so the single file works offline and can be shared as-is. Reads {slug}scenes.json, {slug}images.json, and…
hono-core
Hono ultrafast web framework fundamentals - routing, context, handlers, and response patterns for multi-runtime deployment.