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 SideShiftApp/sideshift-mcp-server --skill sideshift-operationsgit clone --depth 1 https://github.com/SideShiftApp/sideshift-mcp-serverWrote 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/sideshiftapp/sideshift-mcp-server/sideshift-operations)<a href="https://agentmods.dev/skills/sideshiftapp/sideshift-mcp-server/sideshift-operations"><img src="https://agentmods.dev/badge/skills/sideshiftapp/sideshift-mcp-server/sideshift-operations.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 5.1 | $0.00060 | $0.01139 |
| Opus 5 | $0.00030 | $0.00570 |
| Sonnet 5 | $0.00012 | $0.00228 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
sideshift-operations 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 3d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SideShift operations
Use the installed SideShift MCP server as the authoritative interface. Do not replace it with scraped pages, guessed REST calls, direct database access, or another company's credentials.
Establish the operating context
- Call
whoamibefore the first substantive operation in a task. - State the connected company and whether the required scope is present.
- For any write or sensitive operation, verify the company again immediately before execution if the session may have changed.
- If authorization is missing, direct the user through the host's SideShift connection command or setup flow. Never request that the user paste an access token, refresh token, API key, cookie, or client secret into chat.
Select tools from the authoritative catalog
The default server exposes consolidated functions: reads use a *_query function with a documented view; writes have explicit action names. Use the advertised schema and its view options. For example, campaigns_query(view="list") lists campaigns. whoami identifies this surface; it has no hidden catalog to search.
Some connections expose the full direct catalog instead. Use an obvious typed tool first. When no visible tool matches and find_capability (or catalog_search) is available, search by the user's intent, inspect the result with catalog_get_schema, and invoke it through catalog_invoke_read, catalog_invoke_write, or catalog_invoke_sensitive as appropriate.
Never invent a tool name, field, enum value, ID, scope, or outcome. Check the available function views or catalog results before concluding that a capability is unsupported.
Read, write, and sensitive behavior
Reads
Run read-only tools when they directly answer the user's request. Preserve material caveats, pagination, freshness indicators, and not found or insufficient data states.
Writes
Before a reversible write:
- Resolve and show the exact target.
- Load the authoritative schema.
- Gather every required value.
- Summarize the material arguments and expected state change.
- Use an existing explicit authorization when it covers this exact action; otherwise ask for confirmation of the concrete change.
- Execute once, then read back the resulting state when a read tool is available.
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.
- 3d ago Changed · -1 lines 3cbfebee5cac
- 7d ago First seen · 78 lines · 60 tokens per session scan A 2c4fa3fd42f6
sideshift-operations is a skill published in the GitHub repository SideShiftApp/sideshift-mcp-server (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,139 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
stripe
Official Stripe MCP integration for Prime Agent. Connects to Stripe's remote MCP server at https://mcp.stripe.com with OAuth and exposes live Stripe API, billing, reporting, and documentation tools. Use for Stripe test-mode setup, products, prices, customers, subscriptions, billing portal configuration, webhook…
okx-cex-portfolio
This skill should be used when the user asks about 'account balance', 'how much USDT do I have', 'my funding account', 'show my positions', 'open positions', 'position P&L', 'unrealized PnL', 'closed positions', 'position history', 'realized PnL', 'account bills', 'transaction history', 'trading fees', 'fee tier'…
agoragentic-transaction-assurance
Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…
recurrent-payment
A recurring-payment workflow for T-Kassa, a payment service. It links a customer's card during an initial payment and later charges that saved payment authorisation for a subscription.
refund-payment
A payment procedure for refunding a completed T-Kassa payment or cancelling a payment that is still on hold. T-Kassa is a payment service, and the procedure can also send the required closing receipt.
agreement-setup
Set up a bKash tokenized agreement for repeat charges and check its status.