Repository Analysis

docker/docker-agent

AI Agent Builder and Runtime by Docker Engineering

3.5 Likely human-written View on GitHub

Analysis Overview

This report presents the forensic synthetic code analysis of docker/docker-agent, a Go project with 3,240 GitHub stars. SynthScan v2.0 examined 525,168 lines of code across 2282 source files, recording 1429 pattern matches distributed across 12 syntactic categories. The overall adjusted score of 3.5 places this repository in the Likely human-written band.

The scanner applied 160+ deterministic lexical heuristics, multi-line block detectors, abstract syntax tree depth profilers, and a cross-file Jaccard similarity matrix to construct a statistically normalised synthetic code estimate. All matches are individually weighted by severity coefficient and contextual multiplier before summation, and the resulting headline score is temporally discounted to account for the repository's development history relative to the commercial emergence of large language model coding tooling (November 2022 onward).

3.5
Adjusted Score
3.5
Raw Score
100%
Time Factor
2026-08-09
Last Push
3.2K
Stars
Go
Language
525.2K
Lines of Code
2.3K
Files
1.4K
Pattern Hits
2026-08-09
Scan Date
0.01
HC Hit Rate

What These Metrics Mean

Adjusted Score
Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score
The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor
The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits
Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate
High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files
Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

Longitudinal tracking requires multiple scan runs. Once this repository is re-scanned after new commits land, this chart will visualise how the synthetic code signal evolves over time — enabling you to detect whether AI authorship is growing, stabilising, or being actively corrected by human engineers.

No multi-scan history yet — run the scanner again to build trend data.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 0HIGH 21MEDIUM 197LOW 1211

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 1429 distinct pattern matches across 12 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Over-Commented Block1172 hits · 1070 pts
SeverityFileLineSnippetContext
LOWcmd/wasm/runtime_wasm.go1//go:build js && wasmCOMMENT
LOWcmd/wasm/main.go1//go:build js && wasmCOMMENT
LOWcmd/wasm/main.go21// - Open files or listen on sockets.COMMENT
LOWcmd/wasm/main.go41//COMMENT
LOWcmd/wasm/web/auth.js1// OpenRouter PKCE OAuth helpers for the docker-agent wasm browser demo.COMMENT
LOWcmd/wasm/web/auth.js21// scoped, revocable from https://openrouter.ai/settings/keys, and lives onlyCOMMENT
LOWcmd/root/backend.go21// prompt files) and resolves the team.COMMENT
LOWcmd/root/run_listen.go21// in-process runtime even when the HTTP control plane is disabled. That lets aCOMMENT
LOWcmd/root/run.go121 // auto-injector and into the App via app.WithSnapshotController soCOMMENT
LOWcmd/root/run.go541 return runTUI(ctx, rt, sess, b.Spawner(rt), cleanup, f.tuiOpts(args), opts...)COMMENT
LOWcmd/root/run.go1181 // WithToolsApproved before WithSafetyPolicy so a resolved safetyCOMMENT
LOWcmd/root/agent_picker.go581 // agentPickerCardsTop is the number of rows from the panel's top edge toCOMMENT
LOWcmd/root/plans.go381COMMENT
LOWcmd/root/setup.go41// declined or cancelled: the full failure was already printed just above theCOMMENT
LOWcmd/root/setup.go61 // ProviderName and Provider are set when the custom path registered anCOMMENT
LOWcmd/root/sandbox.go201 // package-registry / source-host the auto-installer reaches for.COMMENT
LOWcmd/root/sandbox.go321// default sandbox proxy denies all of them; without this, the innerCOMMENT
LOWcmd/root/sandbox.go501}COMMENT
LOWcmd/root/sandbox.go541// always allowlisted in the sandbox proxy, since every run resolvesCOMMENT
LOWcmd/root/otel.go81COMMENT
LOWcmd/root/otel.go181 return "http://" + endpointCOMMENT
LOWlint/hook_config_sync.go1package mainCOMMENT
LOWlint/hook_config_sync.go21// Drift in either direction is silently broken at runtime:COMMENT
LOWlint/config_version_constant.go1package mainCOMMENT
LOWlint/runtime_session_scoped.go1package mainCOMMENT
LOWlint/constructor_command_exec.go1package mainCOMMENT
LOWlint/slog_contextual.go1package mainCOMMENT
LOWlint/slog_contextual.go21// call's enclosing function:COMMENT
LOWlint/constructor_purity.go1package mainCOMMENT
LOWlint/constructor_purity.go21// accept a context the goroutine honours), so that starting background workCOMMENT
LOWlint/tui_view_purity.go1package mainCOMMENT
LOWlint/tui_view_purity.go21// recv.field = nilCOMMENT
LOWlint/runtime_event_registry.go21// …COMMENT
LOWlint/hook_builtins_registered.go1package mainCOMMENT
LOWlint/hook_builtins_registered.go21//COMMENT
LOWlint/config_latest_tag_consistency.go1package mainCOMMENT
LOWlint/config_latest_tag_consistency.go21// an intentional design choice.COMMENT
LOWlint/config_package_name.go1package mainCOMMENT
LOWdocs/hugo.yaml1# Hugo configuration for https://docker.github.io/docker-agent/COMMENT
LOWdocs/js/app.js41 document.documentElement.removeAttribute('data-theme');COMMENT
LOWexamples/github-copilot.yaml1# GitHub Copilot requires a `Copilot-Integration-Id` header on every requestCOMMENT
LOWexamples/capability-overrides.yaml1# Demonstrates the `capabilities` override for models the models.dev catalogueCOMMENT
LOWexamples/remote_mcp_oauth_callback_redirect.yaml1# Example: Remote MCP server with a custom OAuth callback redirect URL.COMMENT
LOWexamples/filesystem_allow_deny.yaml1# Demonstrates allow_list / deny_list for the filesystem tool.COMMENT
LOWexamples/redact_secrets.yaml1# Demonstrates the redact_secrets feature.COMMENT
LOWexamples/redact_secrets.yaml21# persisted session file, the post_tool_use hook input, or theCOMMENT
LOWexamples/code.yaml21 # 3. **Code Modification**:COMMENT
LOWexamples/compaction_threshold.yaml1# Compaction Threshold ExampleCOMMENT
LOWexamples/custom-pricing.yaml1# Demonstrates the `cost` override that declares a model's token pricingCOMMENT
LOWexamples/readonly.yaml1# Demonstrates the `readonly` attribute on toolsets and agents.COMMENT
LOWexamples/flavors.yaml1#!/usr/bin/env docker agent runCOMMENT
LOWexamples/cached_responses.yaml1# Demonstrates the response cache.COMMENT
LOWexamples/websocket_transport.yaml1# Example: WebSocket Transport for OpenAI Responses APICOMMENT
LOWexamples/handoff.yaml1# Handoff Graph Diagram:COMMENT
LOWexamples/worktree_create_hook.yaml1#COMMENT
LOWexamples/worktree_create_hook.yaml21# files git won't carry over (.env, local config), install dependencies,COMMENT
LOWexamples/bypass_models_gateway.yaml1# Demonstrates `bypass_models_gateway`, which forces a specific model toCOMMENT
LOWexamples/force_handoff.yaml1#!/usr/bin/env cagent runCOMMENT
LOWexamples/mcp_catalog.yaml1# An agent that can discover, enable and use any remote streamable-httpCOMMENT
LOWexamples/miro-expert.yaml1# Example: Miro's hosted MCP server (https://miro.com/ai/mcp/) with skills.COMMENT
1112 more matches not shown…
Modern AI Meta-Vocabulary91 hits · 253 pts
SeverityFileLineSnippetContext
MEDIUMCHANGELOG.md958- [#3451](https://github.com/docker/docker-agent/pull/3451) - feat: add docker agent board, a Kanban TUI for orchestratiCODE
MEDIUMCHANGELOG.md1209- [#3393](https://github.com/docker/docker-agent/pull/3393) - fix: clamp max_tokens to the context window for OpenAI-comCODE
MEDIUMCHANGELOG.md1291- [#3326](https://github.com/docker/docker-agent/pull/3326) - refactor: replace test-mutated globals with dependency injCODE
MEDIUMCHANGELOG.md1499- [#3227](https://github.com/docker/docker-agent/pull/3227) - feat: add plan builtin toolset for shared multi-agent collCODE
MEDIUMCHANGELOG.md1591- [#3227](https://github.com/docker/docker-agent/pull/3227) - feat: add plan builtin toolset for shared multi-agent collCODE
MEDIUMCHANGELOG.md2335- [#2876](https://github.com/docker/docker-agent/pull/2876) - docs: document mcp_catalog toolset and reorganize RAG refeCODE
MEDIUMCHANGELOG.md2673- [#2723](https://github.com/docker/docker-agent/pull/2723) - remote-runtime: close silent gaps, consolidate Runtime, scCODE
MEDIUMCHANGELOG.md2673- [#2723](https://github.com/docker/docker-agent/pull/2723) - remote-runtime: close silent gaps, consolidate Runtime, scCODE
MEDIUMCHANGELOG.md2872- [#2672](https://github.com/docker/docker-agent/pull/2672) - add js/wasm browser build with OpenRouter PKCE, agentic loCODE
MEDIUMCHANGELOG.md2872- [#2672](https://github.com/docker/docker-agent/pull/2672) - add js/wasm browser build with OpenRouter PKCE, agentic loCODE
MEDIUMCHANGELOG.md2996- [#2523](https://github.com/docker/docker-agent/pull/2523) - refactor(runtime): consolidate hook orchestration and cachCODE
MEDIUMCHANGELOG.md3008- [#2535](https://github.com/docker/docker-agent/pull/2535) - refactor(runtime): extract sub-session orchestrationCODE
MEDIUMCHANGELOG.md3463- [#2322](https://github.com/docker/docker-agent/pull/2322) - fix: resolve duplicate RAG tool names and nil pointer paniCODE
MEDIUMCHANGELOG.md3465- [#2324](https://github.com/docker/docker-agent/pull/2324) - fix: pass Models map to RAG ManagersBuildConfig for model CODE
MEDIUMCHANGELOG.md3473- [#2344](https://github.com/docker/docker-agent/pull/2344) - feat: support custom providers in RAG embedding and rerankCODE
MEDIUMCHANGELOG.md3666- [#2210](https://github.com/docker/docker-agent/pull/2210) - Refactor RAG from agent-level config to standard toolset tCODE
MEDIUMCHANGELOG.md3712- [#2205](https://github.com/docker/docker-agent/pull/2205) - Simplify the runtime related RAG code a bitCODE
MEDIUMCHANGELOG.md4265- [#1973](https://github.com/docker/docker-agent/pull/1973) - Fix context window overflow: auto-recovery and proactive cCODE
MEDIUMCHANGELOG.md4353- [#1899](https://github.com/docker/docker-agent/pull/1899) - fix: Esc key not interrupting sub-agents in multi-agent seCODE
MEDIUMcmd/wasm/runtime_wasm.go5// runtime_wasm.go implements a lightweight agentic loop for the browser-basedCOMMENT
MEDIUMcmd/wasm/runtime_wasm.go248// runAgentLoop runs the full agentic loop: stream completions, process toolCOMMENT
MEDIUMcmd/wasm/main.go3// Package main is a js/wasm entry point that exposes docker-agent's agenticCOMMENT
MEDIUMcmd/wasm/main.go8// - A full agentic loop: streaming chat with tool calling, multi-agentCOMMENT
MEDIUMcmd/wasm/main.go223// runChat loads the config, builds the runtime, and runs the agentic loop.COMMENT
MEDIUMcmd/wasm/main.go244 // Run the agentic loop.COMMENT
MEDIUMdocs/configuration/agents/index.md25 toolsets: [list] # Optional: tool configurations (use `type: rag` for RAG sources)CODE
MEDIUMdocs/configuration/agents/index.md35 code_mode_tools: boolean # Optional: let the agent write JavaScript to orchestrate tool calls (see Code Mode)CODE
MEDIUMdocs/configuration/hooks/index.md686### Agent-Switch and Session-Resume: observability for multi-agent and long runsCOMMENT
MEDIUMdocs/configuration/overview/index.md46# 5. RAG — define retrieval-augmented generation sources (optional)COMMENT
MEDIUMdocs/tools/rag/index.md175## Debugging RAGCOMMENT
MEDIUMdocs/tools/rag/index.md197### Top-Level RAG FieldsCOMMENT
MEDIUMdocs/providers/dmr/index.md90 context_size: 32768 # total context window (sent via _configure)CODE
MEDIUMdocs/features/acp/index.md31# With a multi-agent team configCOMMENT
MEDIUMdocs/features/chat-server/index.md28# Pick a specific agent from a multi-agent configCOMMENT
MEDIUMdocs/guides/compaction/index.md11## Why long sessions fill the context windowCOMMENT
MEDIUMdocs/guides/go-sdk/index.md175## RAG Toolset (opt-out)COMMENT
MEDIUMdocs/concepts/distribution/index.md51# Run with a specific agent from a multi-agent configCOMMENT
MEDIUMdocs/concepts/distribution/index.md74See [Pin external sub-agents to a digest](../multi-agent/index.md#pin-external-sub-agents-to-a-digest) and [External SubCODE
MEDIUMexamples/session_context.yaml10# messages, so a big history cannot overflow the context window.COMMENT
MEDIUMexamples/compaction_threshold.yaml7# token usage crosses 90% of the model's context window. Lowering theCOMMENT
MEDIUMexamples/websocket_transport.yaml8# for agentic workflows with many tool calls.COMMENT
MEDIUMexamples/README.md105### RAG (Retrieval-Augmented Generation)COMMENT
MEDIUMexamples/hooks.yaml319 # / cost guardrails / auditing without contributing system messagesCOMMENT
MEDIUMexamples/hooks.yaml26# before_llm_call - just before each model call (observability, guardrails)COMMENT
MEDIUMexamples/compaction_model.yaml21# Note: if the compaction model has a SMALLER context window than the primary,COMMENT
MEDIUMexamples/compaction_model.yaml24# with a compaction model whose context window is at least as large to keep theCOMMENT
MEDIUMexamples/task_budget.yaml2# multi-step agentic task (thinking + tool calls + final output). docker-agentCOMMENT
MEDIUMexamples/chat/main.go20// # or, to pin a specific agent in a multi-agent team:COMMENT
MEDIUMexamples/rag/semantic_embeddings.yaml1# This example demonstrates the semantic-embeddings RAG strategy.COMMENT
MEDIUMexamples/rag/semantic_embeddings.yaml33 # Required: embedding model for vector similarityCOMMENT
MEDIUMexamples/rag/custom_provider.yaml1# This example demonstrates using a custom provider for RAG embedding models.COMMENT
MEDIUMexamples/rag/reranking.yaml11# If reranking fails (e.g., model not available), the RAG system will gracefullyCOMMENT
MEDIUMexamples/rag/hybrid.yaml2# 1. Running multiple retrieval strategies in a single RAG sourceCOMMENT
MEDIUMpkg/config/v8/types.go255 // TaskBudget caps the total tokens a model can spend across an agentic task.COMMENT
MEDIUMpkg/config/v8/types.go622 // TaskBudget caps the total tokens a model can spend across an agentic task.COMMENT
MEDIUMpkg/config/v8/types.go1130// TaskBudget caps the total tokens a model can spend across an agentic taskCOMMENT
MEDIUMpkg/config/v8/types.go1763 // turn_start). Use this for observability, cost guardrails, orCOMMENT
MEDIUMpkg/config/v9/types.go289 // TaskBudget caps the total tokens a model can spend across an agentic task.COMMENT
MEDIUMpkg/config/v9/types.go787 // TaskBudget caps the total tokens a model can spend across an agentic task.COMMENT
MEDIUMpkg/config/v9/types.go1325// TaskBudget caps the total tokens a model can spend across an agentic taskCOMMENT
31 more matches not shown…
Decorative Section Separators80 hits · 242 pts
SeverityFileLineSnippetContext
MEDIUMexamples/handoff.yaml3# ─────> Root Agent <────────<─<─<──────┐COMMENT
MEDIUMexamples/handoff.yaml5# ┌───────┼────────┐ |COMMENT
MEDIUMexamples/handoff.yaml10# | ┌───────┴───────┐ |COMMENT
MEDIUMexamples/handoff.yaml16# | └───────┬───────┘ |COMMENT
MEDIUMexamples/handoff.yaml20# └────────┼───────┘ |COMMENT
MEDIUMexamples/handoff.yaml22# Summarizer ──────>─>─>─────────┘COMMENT
MEDIUMexamples/worktree_create_hook.yaml3# ==========================================================================COMMENT
MEDIUMexamples/anthropic_wif.yaml22 # ---------------------------------------------------------------------COMMENT
MEDIUMexamples/anthropic_wif.yaml28 # ---------------------------------------------------------------------COMMENT
MEDIUMexamples/anthropic_wif.yaml41 # ---------------------------------------------------------------------COMMENT
MEDIUMexamples/anthropic_wif.yaml46 # ---------------------------------------------------------------------COMMENT
MEDIUMexamples/anthropic_wif.yaml57 # ---------------------------------------------------------------------COMMENT
MEDIUMexamples/anthropic_wif.yaml62 # ---------------------------------------------------------------------COMMENT
MEDIUMexamples/anthropic_wif.yaml77 # ---------------------------------------------------------------------COMMENT
MEDIUMexamples/anthropic_wif.yaml88 # ---------------------------------------------------------------------COMMENT
MEDIUMexamples/hooks.yaml247 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml257 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml267 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml272 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml316 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml321 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml330 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml359 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml361 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml371 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml378 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml406 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml409 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml416 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml419 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml429 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml433 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml443 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml449 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml458 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml463 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml472 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml3# ==========================================================================COMMENT
MEDIUMexamples/hooks.yaml103 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml107 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml140 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml144 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml162 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml168 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml182 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml186 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml202 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml208 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml222 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml232 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml287 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml305 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml343 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml389 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml394 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml493 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml508 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml515 # ====================================================================COMMENT
MEDIUMexamples/hooks.yaml528 # ====================================================================COMMENT
MEDIUMexamples/budget.yaml4# ==========================================================================COMMENT
20 more matches not shown…
Magic Placeholder Names19 hits · 100 pts
SeverityFileLineSnippetContext
HIGHdocs/providers/opencode-go/index.md24 export OPENCODE_API_KEY=your-api-keyCODE
HIGHdocs/providers/moonshot/index.md24 export MOONSHOT_API_KEY=your-api-keyCODE
HIGHdocs/providers/baseten/index.md21 export BASETEN_API_KEY=your-api-keyCODE
HIGHdocs/providers/together/index.md24 export TOGETHER_API_KEY=your-api-keyCODE
HIGHdocs/providers/vercel/index.md25 export AI_GATEWAY_API_KEY=your-api-keyCODE
HIGHdocs/providers/openrouter/index.md21 export OPENROUTER_API_KEY=your-api-keyCODE
HIGHdocs/providers/fireworks/index.md24 export FIREWORKS_API_KEY=your-api-keyCODE
HIGHdocs/providers/groq/index.md23 export GROQ_API_KEY=your-api-keyCODE
HIGHdocs/providers/minimax/index.md21 export MINIMAX_API_KEY=your-api-keyCODE
HIGHdocs/providers/deepseek/index.md24 export DEEPSEEK_API_KEY=your-api-keyCODE
HIGHdocs/providers/xai/index.md21 export XAI_API_KEY=your-api-keyCODE
HIGHdocs/providers/nvidia/index.md25 export NVIDIA_API_KEY=your-api-keyCODE
HIGHdocs/providers/nebius/index.md21 export NEBIUS_API_KEY=your-api-keyCODE
HIGHdocs/providers/opencode-zen/index.md23 export OPENCODE_API_KEY=your-api-keyCODE
HIGHdocs/providers/cerebras/index.md25 export CEREBRAS_API_KEY=your-api-keyCODE
HIGHdocs/providers/mistral/index.md21 export MISTRAL_API_KEY=your-api-keyCODE
HIGHdocs/community/opentelemetry/index.md74export OTEL_EXPORTER_OTLP_HEADERS="x-api-key=<your-api-key>,Langsmith-Project=<project>"CODE
HIGHexamples/opencode-zen.yaml6# export OPENCODE_API_KEY="your-api-key"COMMENT
HIGHexamples/opencode-go-practical.yaml6# export OPENCODE_API_KEY="your-api-key"COMMENT
Self-Referential Comments11 hits · 41 pts
SeverityFileLineSnippetContext
MEDIUMcmd/root/alias.go27 Example: ` # Create an alias for a registry agentCODE
MEDIUMcmd/root/alias.go30 # Create an alias for a local agent fileCOMMENT
MEDIUMcmd/root/alias.go75 Example: ` # Create a simple aliasCODE
MEDIUMcmd/root/alias.go78 # Create an alias that always runs in yolo modeCOMMENT
MEDIUMcmd/root/alias.go81 # Create an alias that defaults to the balanced safety modeCOMMENT
MEDIUMcmd/root/alias.go84 # Create an alias with a specific modelCOMMENT
MEDIUMcmd/root/alias.go87 # Create an alias with hidden tool resultsCOMMENT
MEDIUMcmd/root/alias.go90 # Create an alias that always runs in a sandboxCOMMENT
MEDIUMcmd/root/alias.go93 # Create an alias with multiple optionsCOMMENT
MEDIUMexamples/dhi/dhi_mcp_server/server.py6# Define the get_migration_info toolCOMMENT
MEDIUMexamples/elicitation/server.py18# Create the MCP serverCOMMENT
AI Slop Vocabulary14 hits · 38 pts
SeverityFileLineSnippetContext
MEDIUMexamples/code.yaml23 # - Ensure changes follow best practicesCOMMENT
LOWexamples/toolset_instructions.yaml11# If you want to keep the original guidance and just add your own rulesCOMMENT
MEDIUMexamples/multi-code.yaml81 # - Ensure changes follow best practicesCOMMENT
MEDIUMexamples/multi-code.yaml138 # - Ensure changes follow best practicesCOMMENT
MEDIUMe2e/testdata/cassettes/TestExec_DefaultAgent.yaml11 body: "{\"messages\":[{\"content\":[{\"text\":\"Which model are you running? Be super brief.\",\"type\":\"text\"}],\CODE
MEDIUMe2e/testdata/cassettes/TestExec_DefaultAgent.yaml31 body: "{\"max_tokens\":64000,\"messages\":[{\"content\":[{\"text\":\"Which model are you running? Be super brief.\",CODE
MEDIUMpkg/config/resolve.go126// query as volatile — rather than an enumerated denylist — keeps this robust asCOMMENT
MEDIUMpkg/tui/components/markdown/incremental.go296 // the function robust against future refactors of the helpers.COMMENT
MEDIUMpkg/js/expand.go129 // then expand only the text fields. This keeps the expansion robust ifCOMMENT
MEDIUMpkg/selfupdate/exec_unix.go32// descriptors and terminal, so the user sees a seamless restart.COMMENT
MEDIUMpkg/runtime/turn_end_test.go164// is what makes this contract robust: explicit dispatch calls wouldCOMMENT
MEDIUMpkg/hooks/builtins/add_directory_listing_test.go19// format — the test is robust to header tweaks.COMMENT
MEDIUMpkg/modelinfo/resolve_caps_test.go97// by a unique model id to stay robust regardless.COMMENT
MEDIUMpkg/skills/frontmatter.go8// first ": ". This is more robust for the simple frontmatter format used byCOMMENT
Verbosity Indicators10 hits · 22 pts
SeverityFileLineSnippetContext
LOWpkg/tools/builtin/filesystem/filesystem_test.go1434 // Step 1: validate the path while the file is legitimate. This isCOMMENT
LOWpkg/tools/builtin/filesystem/filesystem_test.go1439 // Step 2: attacker (or hostile post-edit hook running between T0 andCOMMENT
LOWpkg/tools/builtin/filesystem/filesystem_test.go1444 // Step 3: at T1 the tool issues the actual write. The rooted writerCOMMENT
LOWpkg/tools/builtin/filesystem/filesystem_test.go1450 // Step 4: the secret must be untouched on disk.COMMENT
LOWpkg/tui/components/messages/messages_test.go1214 // Step 1: Add a reasoning block and a tool call inside it (simulates PartialToolCallEvent)COMMENT
LOWpkg/tui/components/messages/messages_test.go1224 // Step 2: Append an assistant message so the reasoning block is no longer the last messageCOMMENT
LOWpkg/tui/components/messages/messages_test.go1229 // Step 3: Update the tool call to Running (simulates ToolCallEvent)COMMENT
LOWpkg/tui/components/messages/messages.go1543 // Step 1: Handle reasoning content - only create/extend a reasoning block if there's actual reasoningCOMMENT
LOWpkg/tui/components/messages/messages.go1555 // Step 2: Handle assistant content - this breaks the reasoning block chainCOMMENT
LOWpkg/tui/components/messages/messages.go1561 // Step 3: Handle tool callsCOMMENT
Structural Annotation Overuse10 hits · 22 pts
SeverityFileLineSnippetContext
LOWpkg/tools/builtin/filesystem/filesystem_test.go1434 // Step 1: validate the path while the file is legitimate. This isCOMMENT
LOWpkg/tools/builtin/filesystem/filesystem_test.go1439 // Step 2: attacker (or hostile post-edit hook running between T0 andCOMMENT
LOWpkg/tools/builtin/filesystem/filesystem_test.go1444 // Step 3: at T1 the tool issues the actual write. The rooted writerCOMMENT
LOWpkg/tools/builtin/filesystem/filesystem_test.go1450 // Step 4: the secret must be untouched on disk.COMMENT
LOWpkg/tui/components/messages/messages_test.go1214 // Step 1: Add a reasoning block and a tool call inside it (simulates PartialToolCallEvent)COMMENT
LOWpkg/tui/components/messages/messages_test.go1224 // Step 2: Append an assistant message so the reasoning block is no longer the last messageCOMMENT
LOWpkg/tui/components/messages/messages_test.go1229 // Step 3: Update the tool call to Running (simulates ToolCallEvent)COMMENT
LOWpkg/tui/components/messages/messages.go1543 // Step 1: Handle reasoning content - only create/extend a reasoning block if there's actual reasoningCOMMENT
LOWpkg/tui/components/messages/messages.go1555 // Step 2: Handle assistant content - this breaks the reasoning block chainCOMMENT
LOWpkg/tui/components/messages/messages.go1561 // Step 3: Handle tool callsCOMMENT
Fake / Example Data14 hits · 14 pts
SeverityFileLineSnippetContext
LOWcmd/root/setup_test.go191 return &chatgpt.LoginResult{Email: "user@example.com", Plan: "plus"}, nilCODE
LOWpkg/creator/agent_test.go116 "OPENAI_API_KEY=dummy-key-for-testing",CODE
LOWpkg/tools/builtin/api/api_test.go99 Arguments: `{"name":"John Doe","age":30}`,CODE
LOWpkg/tools/builtin/api/api_test.go111 assert.Equal(t, "John Doe", receivedData["name"])CODE
LOWpkg/tui/dialog/elicitation_test.go215 "default": "user@example.com",CODE
LOWpkg/tui/dialog/elicitation_test.go224 Default: "user@example.com",CODE
LOWpkg/runtime/commands_test.go429 input: `name="John Doe" age=30`,CODE
LOWpkg/runtime/commands_test.go430 expected: map[string]any{"name": "John Doe", "age": int64(30)},CODE
LOWpkg/chatgpt/login_test.go88 idClaims["email"] = "user@example.com"CODE
LOWpkg/chatgpt/login_test.go105 assert.Equal(t, "user@example.com", result.Email)CODE
LOWpkg/chatgpt/login_test.go119 assert.Equal(t, "user@example.com", creds.Email)CODE
LOWpkg/chatgpt/chatgpt_test.go54 claims["email"] = "user@example.com"CODE
LOWpkg/chatgpt/chatgpt_test.go62 assert.Equal(t, "user@example.com", parsed.Email)CODE
LOWpkg/chatgpt/chatgpt_test.go86 Email: "user@example.com",CODE
Synthetic Comment Markers2 hits · 12 pts
SeverityFileLineSnippetContext
HIGHpkg/tui/components/sidebar/sidebar.go326 titleRegenerating bool // true when title is being regenerated by AICODE
HIGHpkg/rag/rerank/rerank_test.go54 // Return as many scores as requested documents, falling back to zeros if needed.COMMENT
Example Usage Blocks4 hits · 6 pts
SeverityFileLineSnippetContext
LOWexamples/openapi-petstore.yaml8# Usage:COMMENT
LOWexamples/env_placeholders.yaml12# Usage:COMMENT
LOWexamples/model_env_substitution.yaml9# Usage:COMMENT
LOWscripts/docs-a11y-urls.sh33# Usage:COMMENT
Slop Phrases2 hits · 6 pts
SeverityFileLineSnippetContext
MEDIUMexamples/budget.yaml19# you can try it with an OpenRouter key instead of a first-party provider:COMMENT
MEDIUMexamples/rag/custom_provider.yaml2# For instance, you can use a local Ollama instance or any OpenAI-compatibleCOMMENT