Borrowing it
Nothing to install: this file belongs to patrickjaja/claude-desktop-extra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/patrickjaja/claude-desktop-extra/master/.claude/skills/3p/SKILL.mdgit clone --depth 1 https://github.com/patrickjaja/claude-desktop-extraWrote 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/patrickjaja/claude-desktop-extra/3p)<a href="https://agentmods.dev/skills/patrickjaja/claude-desktop-extra/3p"><img src="https://agentmods.dev/badge/skills/patrickjaja/claude-desktop-extra/3p/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/patrickjaja/claude-desktop-extra/3p"><img src="https://agentmods.dev/badge/skills/patrickjaja/claude-desktop-extra/3p.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Anti-Refusal · line 24 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium Rogue Agent · line 19 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 67 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00143 | $0.01987 |
| Opus 5.5 | $0.00057 | $0.00795 |
| Sonnet 5.5 | $0.00029 | $0.00397 |
| Haiku 4.5 | $0.00014 | $0.00199 |
Grade A, and why
3p 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 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.
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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
3p / enterprise / inference-gateway deployment on Linux
"3p" = third-party / managed deployment: Claude Desktop pointed at a non-Anthropic inference
backend (Bedrock, Vertex, Azure, or a self-hosted gateway like LiteLLM) and/or an MDM-managed config.
On Linux it is driven by /etc/claude-desktop/managed-settings.json.
Minified names below are version-specific (they churn every release - see /linux); anchor on stable
strings. Verified against v1.14271.0.
managed-settings.json (/etc/claude-desktop/managed-settings.json)
The official Linux build reads /etc/claude-desktop/managed-settings.json natively - it ships a Linux
managed-config reader, so we no longer patch the win32-registry/macOS-plist reader the way the old MSIX
pipeline did. (Historical note: on the MSIX, fix_enterprise_config_linux.nim injected a Linux JSON reader
for the old enterprise.json path; that patch and path are obsolete now that the official build does it.)
Schema is documented in memory project_enterprise_json_schema - the load-bearing facts:
- Top-level
managedMcpServersis an array (name+transport+url/command), NOT an object-keyedmcpServersmap (that is silently dropped by the schema parser - no warning). - Inference-gateway keys:
inferenceProvider("gateway"/"bedrock"/"vertex"/…),inferenceGatewayBaseUrl,inferenceGatewayApiKey,inferenceGatewayAuthScheme,inferenceModels(array; first is default),disableDeploymentModeChooser:true. - Any of
inferenceProvider/bootstrapUrlpresent + (disableDeploymentModeChooserOR persisteddeploymentMode!=="1p") flips the app into 3p mode.
What "3p mode" changes (all upstream behavior, not our patches)
| Effect | Why | Our stance |
|---|---|---|
userData -> ~/.config/Claude-3p/ |
Upstream setPath("userData", base+"-3p") at bootstrap, guarded by !process.env.CLAUDE_USER_DATA_DIR. Logs [custom-3p] .... |
Intended - isolates 1p login from 3p. Keep it. (To collapse: export CLAUDE_USER_DATA_DIR in the launcher - it short-circuits the suffix. Not done by default.) |
| Chat tab hidden | chatTabEnabled:A=>A.chatTabEnabled===!0 (strict; default off in 3p). Cowork/Code stay (!==!1). |
Intended. To restore: add "chatTabEnabled": true to managed-settings.json (config-only, no patch). |
3P setup SPA at app://localhost/setup-desktop-3p |
The ion-dist config UI. | fix_ion_dist_linux + fix_marketplace_linux. Config-key schema in baseline/ION.md. |
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 · 90 lines · 143 tokens per session scan A 5d054ee4b54d
3p is a skill published in the GitHub repository patrickjaja/claude-desktop-extra (726 stars, last pushed yesterday), licensed MIT. It adds 143 tokens to every session and 1,987 once invoked, about $0.0006 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 2026-08-30.
3p compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| 3ppatrickjaja/claude-desktop-extra | Skill | 726 | yesterday | MIT | A | 143 | Claude Code |
| calibre-distill-topiccaelum29/calibre-mcp | Skill | 24 | today | MIT | A | 160 | Claude Code |
| calibre-mcp-setupcaelum29/calibre-mcp | Skill | 24 | today | MIT | A | 194 | Claude Code |
| calibre-study-notescaelum29/calibre-mcp | Skill | 24 | today | MIT | A | 243 | Claude Code |
| sipcode-regressAnuj7411/sipcode | Skill | 46 | 21d ago | MIT | A | 105 | Claude Code |
| bastra-recalln0mad-ai/bastra-recall | Skill | 12 | 2d ago | MIT | A | 0 | Codex |
| bastra-recalln0mad-ai/bastra-recall | Skill | 12 | 2d ago | MIT | A | 50 | Codex |