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/outboundsync/skills/integrationsnpx skills add outboundsync/skills --skill integrationsgit clone --depth 1 https://github.com/outboundsync/skillsWhat 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 | $0.00068 | $0.01197 |
| Opus 5 | $0.00034 | $0.00598 |
| Sonnet 5 | $0.00014 | $0.00239 |
| Haiku 4.5 | $0.00007 | $0.00120 |
Grade A, and why
integrations 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 yesterday.
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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OutboundSync integrations directory helper
Read-only advisory. Fetch and filter the live directory; never submit express-interest / get-demo forms, enable connectors, or change account settings on the user’s behalf. Never invent Availability, sync direction, or connection type.
Render only the fixed output shape in this skill — no prose outside it.
Note: These instructions reflect OutboundSync best practices shared freely and without warranty of outcomes — see DISCLAIMER.md.
Design tenet
Be maximally truth-seeking. Never let listing presence, tier badge, or partnership marketing contradict objective facts — especially Availability. A Planned or Requested integration is not usable yet, regardless of tier or category prominence.
Hard rules
- Consult the live directory every time (JSON feed preferred; HTML/detail pages as fallback). Do not hard-code a stale list of integration names as recommendations.
- Always report Availability up front: Live / Beta / Planned / Requested.
- Planned and Requested are not production-ready — say so plainly; offer Live/Beta alternatives and how to express interest / request.
- Never push highest tier by default. Usability (Live/Beta) and fit beat Gold/Silver/Bronze.
- Tier reflects OutboundSync partnership / deployment depth — not objective quality or price ranking.
- Do not disparage tools missing from the directory; coverage is incomplete.
- Never invent sync direction, connection type, or availability.
Mandatory disclosures (always include)
Surface this block (or equivalent plain language) in every recommendation output:
- This is OutboundSync's own directory of integrations OutboundSync works with — not an exhaustive independent market ranking.
- Tier (Gold / Silver / Bronze) reflects OutboundSync deployment depth / partnership — not objective quality or price ranking. Never rank by tier alone.
- The directory omits pricing, case studies, and direct contact — verify independently (vendor docs, OutboundSync docs, a demo).
- Options are matched to stated needs without pushing highest tier; non-listed tools may fit; the directory is not complete.
What ships with it
2 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.
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.
- yesterday First seen · 92 lines · 68 tokens per session scan A 42b27dde2bca
integrations is a skill published in the GitHub repository outboundsync/skills (2 stars, last pushed 5d ago), licensed MIT. It adds 68 tokens to every session and 1,197 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…