Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/manykarim/rf-mcpnpx agentmods add skills/manykarim/rf-mcp/rf-requestsWrote 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/manykarim/rf-mcp/rf-requests)<a href="https://agentmods.dev/skills/manykarim/rf-mcp/rf-requests"><img src="https://agentmods.dev/badge/skills/manykarim/rf-mcp/rf-requests/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/manykarim/rf-mcp/rf-requests"><img src="https://agentmods.dev/badge/skills/manykarim/rf-mcp/rf-requests.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 | $0.00041 | $0.02294 |
| Opus 5.5 | $0.00016 | $0.00918 |
| Sonnet 5.5 | $0.00008 | $0.00459 |
| Haiku 4.5 | $0.00004 | $0.00229 |
Grade A, and why
rf-requests 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RequestsLibrary (API steps)
In rf_repl, import first
The REPL starts with BuiltIn only - Create Session is "not found" until you send Import Library RequestsLibrary (and Import Library Collections), or Import Resource resources/api.resource for project keywords.
Exploring an API without a schema
Without expected_status, a 4xx/5xx raises HTTPError: 422 Client Error ... and the response body (which names the bad field) is NOT in the message. Probe with expected_status=any and log the body:
${r}= POST On Session api /orders json=${body} expected_status=any
Log ${r.status_code} ${r.text}
Every test creates its own data
A test must pass when run alone (rf_run by longname, rerun of failed tests). Never hand ids from one test to the next with Set Suite Variable - "Get Invoice" then fails without "Create Invoice". Put creation in a keyword and call it in each test that needs the record:
Get Invoice Returns Lines
${id}= Create Test Invoice ACME GmbH
${r}= GET On Session api /invoices/${id}
Suite Setup is for what every test only reads (the authenticated session, base data).
Sessions and headers
&{headers}= Create Dictionary X-Workshop-Space=${SHOP_SPACE} X-Session-ID=cart-1
Create Session shop ${SHOP_URL} headers=${headers}
Session headers go with every request; per-request headers=${h} adds to them.
Bodies: pass a dictionary, never JSON text
| Write | Result |
|---|---|
json={"product_id": 1} |
sends the JSON string "{\"product_id\": 1}" - API answers 422 "Input should be a valid dictionary" |
headers={"X-Session-ID": "x"} |
fails: 'str' object has no attribute 'items' |
json=${{ {"product_id": 1, "quantity": 2} }} |
dict - correct (inline Python needs the dict braces inside ${{ }}) |
&{{"k": "v"}} |
fails: SyntaxError: invalid syntax (no dict braces inside) |
&{body}= Create Dictionary product_id=${7} quantity=${3} then json=${body} |
dict with ints - correct |
Create Dictionary quantity=3 |
value is the STRING "3" - use ${3} for numbers, ${True} for booleans |
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 · 149 lines · 41 tokens per session scan A cfcf2e212254
rf-requests is a skill published in the GitHub repository manykarim/rf-mcp (118 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 2,294 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-12.
rf-requests compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rf-requestsmanykarim/rf-mcp | Skill | 118 | yesterday | Apache-2.0 | A | 41 | Claude Code, Codex |
| schema-explorationlangchain-ai/deepagents | Skill | 31k | today | MIT | A | 57 | Claude Code, Codex |
| mempalace-recallMemPalace/mempalace | Skill | 61k | yesterday | MIT | A | 94 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 57k | 5d ago | MIT | A | 44 | Claude Code |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 69k | 8d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| analyze-marketlangchain-ai/deepagents | Skill | 31k | today | MIT | A | 34 | Claude Code, Codex |
| haikuagno-agi/agno | Skill | 43k | today | Apache-2.0 | A | 0 | Claude Code, Codex |