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 j4flmao/agent-skills --skill webhooksgit clone --depth 1 https://github.com/j4flmao/agent-skillsWrote 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/j4flmao/agent-skills/webhooks)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/webhooks"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/webhooks/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/j4flmao/agent-skills/webhooks"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/webhooks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Privilege Escalation · line 96 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Tool Misuse · line 283 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00101 | $0.04065 |
| Opus 5 | $0.00051 | $0.02032 |
| Sonnet 5 | $0.00020 | $0.00813 |
| Haiku 4.5 | $0.00010 | $0.00407 |
Grade A, and why
backend-webhooks scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
return fetch(subscription.url, { How it starts
The opening of the file, as written. The whole thing — 516 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Webhooks
Purpose
Securely receive, verify, retry, and deliver webhooks between services with guaranteed delivery and tamper-proof signatures. Webhooks are the standard mechanism for asynchronous service-to-service event notification.
Agent Protocol
Trigger
Exact user phrases: "webhook", "webhook receiver", "webhook delivery", "signature verification", "HMAC", "event delivery", "outgoing webhook", "incoming webhook", "retry webhook", "webhook endpoint".
Input Context
- Direction: receiving incoming webhooks or sending outgoing webhooks.
- Security requirements (signing, IP allowlisting).
- Expected volume and payload size.
- Event types and schemas.
Output Artifact
Webhook handler code or configuration. No file unless requested.
Response Format
Direction: {incoming|outgoing}
Auth: {HMAC|Basic|OAuth|None}
Retry: {strategy}
Delivery Guarantee: {at-least-once|exactly-once}
Completion Criteria
- Signature verification for incoming webhooks.
- Payload signing for outgoing webhooks.
- Retry with exponential backoff for failed deliveries.
- Dead-letter queue for permanently failed deliveries.
- At-least-once delivery guaranteed.
- Idempotency handling for duplicate deliveries.
Max Response Length
4 lines per webhook. 20 lines for full implementation.
Architecture Decision Tree
Should I Use Webhooks or Polling?
Does the consumer need near-real-time notification?
├── Yes → Webhooks (push-based, lower latency)
└── No → Is the consumer behind a firewall?
├── Yes → Polling (consumer pulls when ready)
└── No → Does the consumer need guaranteed delivery?
├── Yes → Webhooks + retry + DLQ
└── No → Webhooks (best-effort)
Outgoing vs Incoming Webhook Design
Are you sending events to external systems?
├── Yes → Outgoing webhooks:
│ ├── Subscription management (CRUD endpoints)
│ ├── Payload signing (HMAC-SHA256)
│ ├── Retry with backoff (5 attempts)
│ ├── Dead letter queue (after max retries)
│ ├── Rate limiting per subscription
│ └── Consumer-managed endpoint configuration
└── No → Incoming webhooks:
├── Signature verification (timing-safe)
│ ├── Timestamp validation (tolerance window)
│ ├── Payload validation (schema check)
│ ├── Idempotency handling (X-Webhook-ID)
└── Fast acknowledgment (200 before processing)
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.
- references/webhook-delivery.md 5.1 KB
- references/webhook-monitoring.md 3.7 KB
- references/webhook-rate-limiting.md 5.4 KB
- references/webhook-scaling.md 5.8 KB
- references/webhook-security.md 1.6 KB
- references/webhook-setup.md 1.8 KB
- references/webhooks-architecture.md 8.5 KB
- references/webhooks-delivery.md 7.2 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.
- 8d ago First seen · 516 lines · 101 tokens per session scan A ca9b977e421a
backend-webhooks is a skill published in the GitHub repository j4flmao/agent-skills (23 stars, last pushed 5d ago), licensed MIT. It adds 101 tokens to every session and 4,065 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
Service Integration & Contracts
Ensure cross-service integration defines contracts, ownership, failure handling, versioning, and rollout/rollback expectations.
Webhook Automation
Build and manage webhook-based integrations for real-time event processing and API connections.
API Integration Architect
Design, implement, debug, and optimize API integrations with expert-level patterns for REST, GraphQL, webhooks, and authentication flows.
api-connector
Connect to 100+ popular APIs using natural language - automatic authentication, request building, and response parsing.
pilot-webhook-bridge
Forward Pilot Protocol events to HTTP webhooks for Slack, Discord, PagerDuty, and custom integrations. Use this skill when: 1. You need to forward Pilot events to external services (Slack, Discord, Teams) 2. You need to integrate with monitoring/alerting platforms (PagerDuty, Datadog) 3. You need to trigger external…
webhook-subscriptions
Webhook subscriptions: event-driven agent runs.