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 skills add randommonicle/claude-skills --skill server-side-authoritygit clone --depth 1 https://github.com/randommonicle/claude-skillsWrote 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/randommonicle/claude-skills/server-side-authority)<a href="https://agentmods.dev/skills/randommonicle/claude-skills/server-side-authority"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/server-side-authority/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/randommonicle/claude-skills/server-side-authority"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/server-side-authority.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00147 | $0.00702 |
| Opus 5 | $0.00073 | $0.00351 |
| Sonnet 5 | $0.00029 | $0.00140 |
| Haiku 4.5 | $0.00015 | $0.00070 |
Grade A, and why
server-side-authority 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 10d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Server-side authority
Four rules from an independent security audit's transferable findings, including a role-escalation the audit called its most urgent single change and an IDOR pattern that recurs across repos. Added by committee decision (2-1, dissent recorded in the review record) as one narrow skill rather than four broad ones.
Rule 1 — derive paths and ids server-side from the owned row
Never download, mutate, or serve whatever path or id the client sent, even after checking
the caller owns a related record. A photo-analysis route once verified the caller owned the
photo row, then downloaded whatever storage_path the request carried — an access-confusion
hole. The owned row already knows its own path; read it from there.
Rule 2 — RLS self-update policies scope columns, not just rows
UPDATE ... WHERE auth.uid() = id with no column restriction lets a user set their own
role to admin. Restrict the writable columns — a trigger rejecting privileged-column
changes, or a column-level REVOKE — not only the row. Row-scoping answers "which records";
it says nothing about "which fields".
Rule 3 — every exposed table: RLS enabled, or grants revoked
A public-schema table is reachable through the API layer regardless of what the code comments assert. "The anon key never touches this table" is a comment, not a control (enforce-invariants-in-build applies). Either enable RLS with real policies or revoke the role grants — and verify from the catalog, not the comment.
Rule 4 — escape all dynamic output in admin surfaces
Escaping only the fields you consider user-supplied leaves the rest as a stored-XSS path into the most privileged session in the system. Names, emails, job titles, and addresses are attacker-writable too. Escape everything dynamic, uniformly, at the render boundary.
What this skill does not do
It does not replace a full security review (the security-review command exists for that), govern client-side validation, or cover the wider audit programme (backups, transfers, seed-data hygiene stay project-side). Four rules, checked at the moments named in the trigger.
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.
- 10d ago First seen · 53 lines · 147 tokens per session scan A eba156bed2a8
server-side-authority is a skill published in the GitHub repository randommonicle/claude-skills (23 stars, last pushed 3d ago), licensed Apache-2.0. It adds 147 tokens to every session and 702 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
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
agui-dotnet-protobuf
Use the protobuf wire transport (instead of the default Server-Sent Events) for an AG-UI connection with the AG-UI .NET SDK — a compact binary event stream negotiated via the Accept header. USE FOR: making an AGUIChatClient prefer protobuf by wiring an AGUIEventStreamHandler with ProtobufEventStreamFormatter (then…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
fastapi-router-py
Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models. Use when building REST API endpoints, creating new routes, implementing CRUD operations, or adding authenticated endpoints in FastAPI applications.
migrate-segw-to-rap
Reverse-engineer a SEGW-built OData V2 service (MPC/DPC/MPCEXT/DPCEXT) into a modern RAP V4 service — tables, CDS views (interface + projection), behavior definitions, draft entities, service definition + binding. Use when asked to "migrate this SEGW service to RAP", "convert OData V2 to V4 RAP", "modernize this…
telnyx-messaging-hosted-curl
Set up hosted SMS numbers, toll-free verification, and RCS messaging. Use when migrating numbers or enabling rich messaging features. This skill provides REST API (curl) examples.