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/tomaspozo/agentlink/notificationsnpx skills add tomaspozo/agentlink --skill notificationsgit clone --depth 1 https://github.com/tomaspozo/agentlinkWhat 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 | $0.00144 | $0.01969 |
| Opus 5 | $0.00072 | $0.00984 |
| Sonnet 5 | $0.00029 | $0.00394 |
| Haiku 4.5 | $0.00014 | $0.00197 |
Grade A, and why
notifications 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notifications (Transactional Email)
App-driven emails — welcome, "your export is ready", "payment failed", receipts,
digests, alerts. Anything fired by your code or a DB event, as opposed to
Supabase Auth's own emails (those go through the auth skill's email hook).
The infrastructure already exists in every scaffolded project. You do not build a queue, a worker, a cron, or a retry loop — you register a template and call one RPC.
The one rule: send from the server, never the client
Transactional email is service-role only. The entry point —
api._admin_send_email(...) — is SECURITY DEFINER, granted to service_role,
and revoked from anon/authenticated. Fire it from a DB trigger, another
SECURITY DEFINER function, or a secret-auth edge function. Never expose an
RPC that lets a client send arbitrary email (recipient + content) — that is a spam
and spoofing vector. The events that need email (signup, export done, payment
failed) originate server-side anyway.
How it flows
server-side event ─→ api._admin_send_email('<email_id>', recipient, params, dedupe_key)
│ inserts public.internal_logs_email (status 'queued', unique dedupe_key)
│ enqueues api._admin_enqueue_task('internal-send-email', { log_id })
▼
internal-queue-worker (existing, generic) ──invoke──▶ internal-send-email
│ loads the log row (api._admin_email_log_get)
│ if status='sent' → skip (idempotent); else: TEMPLATES[email_id] → render → Resend.send
▼
api._admin_email_log_mark(log_id, 'sent'|'failed', resend_id, error)
This reuses the same queue + worker that powers auth emails and workspace
invites. PGMQ's visibility-timeout + read_ct already give you retry-with-backoff
and a dead-letter (archive) after QUEUE_MAX_RETRIES — see the
edge-functions and database
skills for the queue/worker model. The 1-minute cron is only a safety net;
api._admin_send_email fires the worker immediately via pg_net, so latency is
seconds, not a minute.
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.
- 2d ago First seen · 128 lines · 144 tokens per session scan A 6f301dc74775
notifications is a skill published in the GitHub repository tomaspozo/agentlink (6 stars, last pushed 1mo ago), licensed MIT. It adds 144 tokens to every session and 1,969 once invoked, about $0.0007 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…