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 sigcli/sigcli --skill xiaohongshugit clone --depth 1 https://github.com/sigcli/sigcliWrote 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/sigcli/sigcli/xiaohongshu)<a href="https://agentmods.dev/skills/sigcli/sigcli/xiaohongshu"><img src="https://agentmods.dev/badge/skills/sigcli/sigcli/xiaohongshu/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/sigcli/sigcli/xiaohongshu"><img src="https://agentmods.dev/badge/skills/sigcli/sigcli/xiaohongshu.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 25 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 153 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 155 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 156 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 157 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 159 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 160 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 161 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Prompt Injection · line 153 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 153 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 155 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 155 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 157 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 159 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 156 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 156 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 157 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 159 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 160 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 161 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 161 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00135 | $0.04033 |
| Opus 5.5 | $0.00054 | $0.01613 |
| Sonnet 5.5 | $0.00027 | $0.00807 |
| Haiku 4.5 | $0.00014 | $0.00403 |
Grade A, and why
xiaohongshu scanned grade A with 1 finding 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
'curl -sL -H "Cookie: $SIG_XIAOHONGSHU_COOKIE" -H "User-Agent: Mozilla/5.0" \ How it starts
The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Xiaohongshu
Search notes, read note details, view comments, browse user profiles, and get the home feed from Xiaohongshu (小红书).
Skill Directory
<SKILL_DIR> is the directory containing this SKILL.md file. Determine it ONCE at the start and reuse it.
Setup (run FIRST — every time, before any operation)
You MUST complete this setup before running any script. Do NOT skip.
sig status xiaohongshu 2>&1
Check the JSON output fields configured and valid:
configured: false→ run Provider Setup below.valid: false(but configured: true) → runsig login xiaohongshu --mode visible, complete the captcha, then re-check.valid: true→ run Vendor Setup (one-time per machine), then execute the user's request.
Provider Setup
- Read
<SKILL_DIR>/references/provider-config.yaml - Append the provider block to
~/.sig/config.yamlunderproviders: - Run
sig login xiaohongshu --mode visible— a browser opens; scan the QR code with the Xiaohongshu app and complete the slider/image captcha if prompted - Verify:
sig status xiaohongshushould showvalid: true
Why the validateRule is so picky — three response shapes
/api/sns/web/unread_count is a permissive endpoint that hides a "partially expired cookie" state behind what looks like a successful response. The provider's validateRule is built specifically to reject it:
| State | /api/sns/web/unread_count returns |
Detected as |
|---|---|---|
| Healthy cookie | {code:0, success:true, data:{unread_count:N, likes:N, ...}} |
✅ valid |
| Cookie partially expired | {code:0, success:true, data:{}} |
❌ rejected by Object.keys(data).length > 0 |
| Cookie fully expired / logged out | {code:-101, success:false, msg:"无登录信息"} |
❌ rejected by code === 0 |
What ships with it
29 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.
- references/provider-config.yaml 2.5 KB
- requirements.txt 60 B
- scripts/sync-vendor.sh 4.2 KB runs code
- scripts/xiaohongshu_client.py 7.3 KB runs code
- scripts/xiaohongshu_get_homefeed.py 1.6 KB runs code
- scripts/xiaohongshu_get_note_comments.py 1.3 KB runs code
- scripts/xiaohongshu_get_note_info.py 1.2 KB runs code
- scripts/xiaohongshu_get_user_info.py 1.1 KB runs code
- scripts/xiaohongshu_get_user_notes.py 1.5 KB runs code
- scripts/xiaohongshu_search_note.py 1.6 KB runs code
- vendor/__init__.py 0 B runs code
- vendor/apis/__init__.py 0 B runs code
- vendor/apis/xhs_pc_apis.py 43 KB runs code
- vendor/LICENSE 1.1 KB
- vendor/package.json 90 B
- vendor/static/xhs_a1.js 19 KB runs code
- vendor/static/xhs_main_260411.js 1107 KB runs code
- vendor/static/xhs_rap.js 435 KB runs code
- vendor/static/xhs_websectiga_env.js 4.6 KB runs code
- vendor/static/xhs_xray_pack1.js 3775 KB runs code
- vendor/static/xhs_xray_pack2.js 1964 KB runs code
- vendor/static/xhs_xray.js 18 KB runs code
- vendor/UPSTREAM.md 749 B
- vendor/xhs_utils/__init__.py 0 B runs code
- vendor/xhs_utils/common_util.py 3.8 KB runs code
- vendor/xhs_utils/cookie_util.py 267 B runs code
- vendor/xhs_utils/data_util.py 12 KB runs code
- vendor/xhs_utils/http_util.py 21 B runs code
- vendor/xhs_utils/xhs_util.py 5.0 KB runs code
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.
- 2mo ago First seen · 284 lines · 135 tokens per session scan A 1c4737029a23
xiaohongshu is a skill published in the GitHub repository sigcli/sigcli (292 stars, last pushed 1mo ago), licensed MIT. It adds 135 tokens to every session and 4,033 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…
browser-skill
Use a real web browser - read pages through their accessibility tree, click and type by reference, call the tools a site offers (WebMCP), and hand the page to the owner for logins, CAPTCHAs and final confirmations.