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/rpcnpx skills add tomaspozo/agentlink --skill rpcgit 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 | $0.00089 | $0.03877 |
| Opus 5 | $0.00044 | $0.01938 |
| Sonnet 5 | $0.00018 | $0.00775 |
| Haiku 4.5 | $0.00009 | $0.00388 |
Grade A, and why
rpc 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RPC-First Data Access
Every data operation is a function in the api schema. No .from(). No direct table queries. No views. The api schema is the only schema exposed via the Supabase Data API — tables in public are invisible. This applies to all code: frontend components, edge functions, webhooks, cron jobs, server routes — no exceptions.
// ❌ WRONG — .from() cannot reach tables (public schema is not exposed)
const { data } = await supabase.from("charts").select("*");
// ❌ ALSO WRONG — even with service role key, .from() won't reach public tables
const admin = createClient(url, secretKey, { db: { schema: "public" } });
const { data } = await admin.from("charts").select("*");
// ✅ CORRECT
const { data } = await supabase.rpc("chart_get_by_user");
// ✅ CORRECT — within withSupabase context
const { data } = await ctx.supabase.rpc("chart_get_by_user");
const { data } = await ctx.supabaseAdmin.rpc("chart_admin_cleanup");
Function Anatomy
Every api schema function follows this structure:
CREATE OR REPLACE FUNCTION api.chart_get_by_id(p_chart_id uuid)
RETURNS jsonb
LANGUAGE plpgsql
SECURITY INVOKER
SET search_path = ''
AS $$
DECLARE
v_result jsonb;
BEGIN
SELECT jsonb_build_object(
'id', c.id,
'name', c.name,
'created_at', c.created_at
) INTO v_result
FROM public.charts c
WHERE c.id = p_chart_id;
IF v_result IS NULL THEN
RAISE EXCEPTION 'Chart not found: %', p_chart_id;
END IF;
RETURN v_result;
END;
$$;
Key rules:
api.schema — all data access functions live hereSECURITY INVOKER— runs as the caller; isolation RLS applies automatically- Permission gate first — mutating RPCs
PERFORM public.auth_verify_access('<entity>.<action>')as the first statement, then scope queries withWHERE tenant_id = (SELECT public._auth_tenant_id()). Permissions live in the RPC, not in RLS (which is isolation-only). SET search_path = ''— prevents search path injection- Fully qualified names —
public.charts,public._auth_*,public._internal_admin_*— never bare names - Grant EXECUTE per function — every
apiRPC (default-deny, like tables; there is no schema-wideGRANT ON ALL FUNCTIONS). After the definition addREVOKE ALL ON FUNCTION api.<fn>(<arg-types>) FROM PUBLIC;thenGRANT EXECUTE ON FUNCTION api.<fn>(<arg-types>) TO authenticated, service_role;. The REVOKE strips Postgres' built-inPUBLICEXECUTE (soanoncan't reach it); a forgotten grant fails fast (42501). Anon-callable RPC:GRANT … TO anon, authenticated, service_roleand make itSECURITY DEFINER.api._admin_*(service_role-only):REVOKE … FROM PUBLIC, anon, authenticated; GRANT EXECUTE … TO service_role(also silences DEFINER lint 0028). See the Grants section inreferences/rpc_patterns.md. p_prefix on parameters,v_prefix on local variables
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.
- 2d ago First seen · 275 lines · 89 tokens per session scan A c9e33ca79bfc
rpc is a skill published in the GitHub repository tomaspozo/agentlink (6 stars, last pushed 1mo ago), licensed MIT. It adds 89 tokens to every session and 3,877 once invoked, about $0.0004 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…