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/build-mcpbnpx skills add webhook-co/webhook --skill build-mcpbgit 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 | $0.00052 | $0.00523 |
| Opus 5 | $0.00026 | $0.00262 |
| Sonnet 5 | $0.00010 | $0.00105 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
build-mcpb 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.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Build MCPB
MCPB packages a local stdio MCP server into a single installable bundle a user can drop into an
MCP host. Use it only when the server must run on the user's machine — the clearest case here is
tooling that rides with the CLI / tunnel client and needs local environment access. For anything
that can run server-side, prefer the remote streamable-HTTP server on Workers (see
build-mcp-server); don't package something as MCPB just to avoid hosting it.
When MCPB is the right call
- The server needs the user's local filesystem, processes, or network position (e.g. replay-to- localhost tooling) that a remote Worker can't reach.
- You want one-step install for a stdio server instead of asking users to clone and wire up a runtime.
If neither is true, it belongs on Workers as a remote server.
Packaging checklist
- The server runs over stdio and starts cleanly with no manual setup beyond the bundle.
- The manifest declares name, version, entry point, and the inputs/secrets it expects — with clear placeholders, never real tokens or account/zone IDs.
- Secrets are requested at install/runtime and read from the environment; nothing sensitive is baked into the bundle.
- Tool contracts and types match the other surfaces (
shared/); the bundle is a packaging of an existing capability, not a divergent one. - Versioning + a smoke test: the bundle installs and the tools respond on a clean machine.
Guardrails
- MCP/AI-native parity: a locally-bundled capability still exists on CLI/API/web/MCP at parity.
- Standard-Webhooks-native signing/verification; no hand-rolled schemes shipped in the bundle.
- Private-by-default and public-safe: no secrets, account/zone IDs, or pricing details in the manifest or bundled code.
- A local server is still subject to the same validation and redaction rules — never log full payloads or PII/PHI.
Progressive disclosure
Keep the manifest template, signing/distribution steps, and a clean-machine install drill 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 · 45 lines · 52 tokens per session scan A b90e1977251c
build-mcpb is a skill published in the GitHub repository webhook-co/webhook (0 stars, last pushed 7d ago), licensed Apache-2.0. It adds 52 tokens to every session and 523 once invoked, about $0.0003 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
flaim-fantasy
Use when a user wants analysis of a Flaim-connected ESPN, Yahoo, or Sleeper fantasy league, or help with Flaim setup, capabilities, or permissions. This includes rosters, standings, matchups, available players, transactions, historical seasons, and lineup, waiver, or trade advice. Do not use for generic sports news…
mcp-migration
Diagnose and carry out the migration of an MCP server to the 2026-07-28 specification — the revision that made the transport stateless, formalized OAuth 2.1, and deprecated the logging, sampling, and roots capabilities. Use this skill whenever someone mentions migrating, upgrading, or checking an MCP server against…
activity-brief
Give a time-bucketed league activity briefing on recent fantasy moves, including who moved who, when, and why. Use when the user explicitly wants a transaction roundup or invokes /activity-brief.
analyze-matchup
Analyze the current fantasy matchup with scores, remaining players or games, and a fact-based forecast. Use when the user explicitly wants a matchup-state breakdown or invokes /analyze-matchup.
gw1-build-assistant
Use when the user asks about Guild Wars 1 (the original 2005 game, not GW2) — designing or reviewing skill bars, decoding or producing template codes (strings like "OgCjkurIrSuXaXPXBYihygvlYcA"), hero team composition, skill lookups or comparisons, or pasting a paw-ned2 team blob ("pwnd0001..."). Use the gw1-mcp tools…
sandbox-sdk
Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs…