# Cline docs: AI Agent Readiness Score 80.0% (B-) **80.0% · 64/80 · AI Agent Readiness Score · 24/30 reading points · 40/50 agent surface points** Cline received 10 PASS votes and passed 4 of five agent surface checks. The clearest finding came from the find the exact limits task. - Tested: 2026-08-20 - Published: 2026-09-21 - Battery: v1 - Scoring: reading 30 pts · surface 50 pts - Docs: https://docs.cline.bot/cline-overview Three AI models, GPT 5.6 Sol, Claude Opus 5, and DeepSeek v4 Flash, each read Cline’s public documentation independently and attempted five first-hour developer jobs: build the first IDE task, find the exact limits, recover from a 429, authenticate the Cline API, use the Cline SDK. No accounts, API calls, or code execution were used. Every verdict came from public pages and every published quotation passed a live verification check. Preflight substitutions: T4: Cline API authentication replaces webhooks. ## Freshness [How rechecks work](https://docsforagents.com/methodology/#freshness) - Category: [Coding agents](https://docsforagents.com/grades/?category=coding-agents) - Tested: 2026-08-20 - Quotes verified: 2026-08-20 - Surface rechecked: 2026-09-21 No confirmed change since the test. 5 of 5 quoted passages still appear on the live pages. ## Agent surface checks · 40/50 | Check | Verdict | Points | | --- | --- | --- | | llms.txt | PASS | 10 | | llms-full.txt | PASS | 10 | | Markdown mirror | PASS | 10 | | MCP server | PASS | 10 | | Docs AI | FAIL | 0 | ## The Reading Test · 24/30 | Task | GPT 5.6 Sol | Opus 5 | DeepSeek v4F | Consensus | | --- | --- | --- | --- | --- | | Build the first IDE task | PASS | PARTIAL | PASS | PASS | | Find the exact limits | FAIL | PARTIAL | PARTIAL | PARTIAL | | Recover from a 429 | PARTIAL | PASS | PASS | PASS | | Authenticate the Cline API | PASS | PASS | PASS | PASS | | Use the Cline SDK | PASS | PASS | PASS | PASS | Docs platform: Mintlify (unscored) · verified 2026-08-20 ## What to fix first These 2 fixes could add up to 14 points to the AI Agent Readiness Score. The list ranks each fix by the points it would add. [How the ranking works](https://docsforagents.com/methodology/#what-to-fix-first) 1. **+10 points · Docs AI · check failed** **Found:** The live Mintlify configuration disables AI chat. **Fix:** Add an assistant to the docs site that answers questions from the docs and links to its sources. 2. **+4 points · Find the exact limits · PARTIAL** **Found:** The ClinePass page names 5-hour, weekly, and monthly limits without amounts, and the API reference gives no numeric rate limit. **Fix:** State the ClinePass usage allowed in each 5-hour, weekly, and monthly window, and publish the Cline API rate limits. **Evidence:** [docs.cline.bot/getting-started/clinepass](https://docs.cline.bot/getting-started/clinepass) ## What the docs get right - **Authenticate the Cline API: 3 PASS votes.** One page explains key creation, the Bearer header, programmatic use, and automatically managed account tokens. - **Use the Cline SDK: 3 PASS votes.** The quickstart installs @cline/sdk, configures Anthropic and a model, subscribes to assistant-text-delta, and calls agent.run. - **4 of 5 agent surface checks.** Present: llms.txt, llms-full.txt, markdown mirrors, an MCP server. Missing: docs AI. ## Build the first IDE task **PASS** PASS consensus from 2 PASS, 1 PARTIAL. The install, provider, todo, Act-mode, diff, approval, and Compare instructions form one complete path. The VS Code path is complete end to end, but the install page and the overview page link to two different JetBrains marketplace listings for the same plugin, so a JetBrains reader has to guess which one is current. The docs provide a complete click-by-click walkthrough from IDE extension install through provider authorization, the todo app prompt, Plan vs Act mode, approval, and checkpoint review. ## Find the exact limits **PARTIAL** PARTIAL consensus from 2 PARTIAL, 1 FAIL. The docs list price and model rates, but omit quotas and API limits; both linked API assets failed to load. The $9.99/month price and the per-1M-token reference rates are exact, but the three ClinePass quota windows are defined circularly with no magnitude, and no page in the API reference states a numeric Cline API rate limit. ClinePass price ($9.99/month) and model reference rates are documented, but no exact numerical quota values are given for the three limit windows, and Cline API rate limits are described only qualitatively (add delays, reduce concurrency). ## Recover from a 429 **PASS** PASS consensus from 2 PASS, 1 PARTIAL. The page covers 429s, concurrency, and streaming, but its 1-second table conflicts with the sample’s 2-second initial delay. One page supplies the retryable status list, a runnable exponential-backoff function, the instruction to reduce concurrent requests, and the rate_limit mid-stream code, though no Retry-After header is documented. The errors page documents the 429 status, provides a complete Python exponential backoff code example, advises reducing concurrency, and covers mid-stream rate_limit errors with finish_reason: 'error' plus a warning to always check finish_reason in streaming handlers. ## Authenticate the Cline API **PASS** PASS consensus from 3 PASS. One page explains key creation, the Bearer header, programmatic use, and automatically managed account tokens. Key creation at Settings > API Keys, the Bearer header format, and the API-key versus account-auth-token distinction are all stated on one page with matching curl examples. The authentication page provides a comparison table distinguishing API keys from account auth tokens, step-by-step key creation, and shows the Bearer token header format used in every request. ## Use the Cline SDK **PASS** PASS consensus from 3 PASS. The quickstart installs @cline/sdk, configures Anthropic and a model, subscribes to assistant-text-delta, and calls agent.run. The quickstart's provider, model, subscribe, and run calls match the Agent reference, which confirms Agent is an alias for AgentRuntime re-exported from @cline/sdk. The SDK overview page provides a complete working 'Your First Agent' example that installs the SDK, configures a provider and model, subscribes to assistant-text-delta events, and runs an agent task. ## The receipt > 5-hour rolling window — your usage within rolling 5-hour period The $9.99/month price and the per-1M-token reference rates are exact, but the three ClinePass quota windows are defined circularly with no magnitude, and no page in the API reference states a numeric Cline API rate limit. - [docs.cline.bot/getting-started/clinepass](https://docs.cline.bot/getting-started/clinepass) ## Agent surface notes Initialize returned a valid MCP response with Cline server information. The live Mintlify configuration disables AI chat. ## Method note This is a reading test of public documentation, not an execution test. No accounts were created and no API calls were run. The AI Agent Readiness Score counts fifteen reading votes at PASS 2, PARTIAL 1, and FAIL 0, for 30 possible points. Five agent surface checks add 10 points each. The total is 80. Consensus chips show each row majority and do not affect scoring. The panel split on 3 of five tasks. Quotes shown here were re-fetched and confirmed verbatim on 2026-08-20. Methodology: https://docsforagents.com/methodology/ Canonical URL: https://docsforagents.com/reports/cline-docs-ai-agent-readiness/