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/getpostern/postern/new-connectornpx skills add getpostern/postern --skill new-connectorgit clone --depth 1 https://github.com/getpostern/posternWrote 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/getpostern/postern/new-connector)<a href="https://agentmods.dev/skills/getpostern/postern/new-connector"><img src="https://agentmods.dev/badge/skills/getpostern/postern/new-connector.svg" alt="Measured on agentmods" 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 | $0.00039 | $0.01356 |
| Opus 5 | $0.00019 | $0.00678 |
| Sonnet 5 | $0.00008 | $0.00271 |
| Haiku 4.5 | $0.00004 | $0.00136 |
Grade A, and why
new-connector 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adding or changing a connector
The contract is already code — read it, don't re-derive it
src/sdk/contract.ts → CONTRACT_OBLIGATIONS is the machine-readable contract (H1–H8 + H-types enforced by the runner; S1–S12 convention, made mechanical by the harness). src/sdk/README.md is its prose mirror and carries the 4-step "how to add a connector (and prove it conforms)" recipe — follow that, and read the per-member JSDoc in src/connectors/types.ts rather than any summary of it.
The harness is describeConformance from src/sdk/index.js: a contract layer (pure, no DB, no transport, drives your ConformanceFixtures) plus an optional integration layer that drives the real syncConnection through your own mock to prove H6/H7/H8/S1/S2. src/connectors/icloud-calendar.conformance.ts + .conformance.test.ts is the smallest complete pair to model on; the Home Assistant exemption (a push connector that owns its own writes) is documented in the README.
⚠️ docs/agent-authored-connectors.html:151 renders a Connector interface with three members (sync/normalize/strongKeys). That is positioning material for readers, NOT the contract. The real interface is src/connectors/types.ts:131 and has twelve members. Build from the HTML and you build the wrong thing.
The golden-fixture rule — the one that has actually bitten
Faked-transport tests cannot catch a real provider's response shape. They assert that your code handles the shape your fake emits, which is the shape your code already expects. That is a tautology, and it shipped a connector that stored zero rows.
The iCloud DAV connector passed its whole suite green and then stored 0 rows against real iCloud: dav-core read bodies off the on-the-wire kebab key calendar-data, but tsdav camelCases response elements to calendarData and CDATA-wraps the body as {_cdata: "..."}. Only the live smoke caught it. The fix and the warning now live at src/connectors/dav-core.ts:255.
So, for any new source:
What ships with it
1 file 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.
- 4d ago First seen · 52 lines · 39 tokens per session scan A 6075afe5ecb7
new-connector is a skill published in the GitHub repository getpostern/postern (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 1,356 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
release-checklist
Pre-release safety audit for the Bifrost repo. Scans database migrations changed in a release for high-scale deadlock / lock-contention risks and for work that blocks application boot time, then produces a pass/warn/fail report with a concrete remediation plan. Invoked with /release-checklist [git-ref-range]. Built to…
n8n:db-migrations
Authors n8n database migrations. Use when creating or modifying files under packages/@n8n/db/src/migrations/, when the user asks to add a column, table, index, foreign key, or backfill, or when the user mentions DB migrations or TypeORM migrations.
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
api-mirror
Stand up a persistent, self-refreshing local mirror of a bulk upstream dataset with the MirrorService (@cyanheads/mcp-ts-core/mirror). Use when a server wraps a large or slow API and should query a synced local index (embedded SQLite + FTS5) instead of paginating the live API per request.
seed-test-data
Seed reproducible local Langfuse data in ClickHouse and Postgres. Use for complex traces, long sessions, v3/v4 events, bulk list data, or frontend rendering and performance tests; never use ad hoc scripts or raw inserts.
data-analyst
Connects to databases, runs SQL queries, and analyzes datasets using code to provide actionable business insights.