Claude Code
- Surfaces represented
- Claude Code terminal CLI · Claude Code IDE integrations
- Model context represented
- Not established
Practical agent comparison
Claude Code vs Gemini CLI
Both products document hierarchical project guidance, coding tools, filesystem changes, shell execution, and permission controls. Claude Code uses scoped CLAUDE.md files and repository auto memory. Gemini CLI uses hierarchical GEMINI.md context and documents planning and web tools; the reviewed evidence does not establish comparable persistent memory. Their confirmation, sandbox, and context-assembly mechanisms differ, so preserve the destination product's control model when migrating workflows.
- Reviewed
- Products
- Claude Code · Gemini CLI
- Decision criteria
- 9 reviewed questions
Comparison orientation
Four reviewed dimensions at a glance
Each dimension links to its detailed evidence row. State labels describe the selected evidence.
Left productClaude CodeOpen product record
- Documented 01Repository / project instructionsOpen detailed evidence Documented
- Documented 02Memory / persistent contextOpen detailed evidence Not established
- Not established 03Planning / work decompositionOpen detailed evidence Documented
- Documented 04Tools / tool callingOpen detailed evidence Documented
Who this comparison is for
How do Claude Code and Gemini CLI assemble documented instructions and controls?
Developers and engineering teams comparing multi-surface Claude Code workflows with terminal-based Gemini CLI automation.
Evidence-bounded scope
Product, surface, and model context
These summaries combine only the scope stated in the reviewed answers. Each criterion keeps its narrower limits.
Gemini CLI
- Surfaces represented
- Gemini CLI
- Model context represented
- Not established
Practical behavior comparison
What the selected evidence establishes
“Not established” records an evidence gap. It does not mean the product lacks the capability.
| Criterion | Claude Code | Gemini CLI | Practical implication |
|---|---|---|---|
| Repository / project instructions Repository guidance must be placed in the target agent's documented instruction hierarchy. | Documented Scoped CLAUDE.md hierarchy
| Documented Hierarchical GEMINI.md context
| Editorial implication Both products document hierarchical repository guidance. Map CLAUDE.md and GEMINI.md scopes instead of treating the filenames as interchangeable. Review scope and limits |
| Memory / persistent context Durable workflow context should not be assumed to persist across agent environments. | Documented Repository-scoped auto memory
| Not established Persistent memory semantics not established
| Editorial implication Claude Code documents repository auto memory; comparable Gemini CLI persistence is not established. Keep required durable context outside assumed memory when moving work. Review scope and limits |
| Planning / work decomposition Planning assumptions shape how teams structure, review, and resume multi-step work. | Not established Planning procedure not established
| Documented Planning appears in documented tools
| Editorial implication Gemini CLI planning appears in the selected tool reference; a specific Claude Code procedure is not established. Define the plan artifact explicitly for both. Review scope and limits |
| Tools / tool calling A portable workflow must use only the tools established by the selected evidence. | Documented Read, edit, execute, and external tools
| Documented Filesystem, execution, planning, MCP, and web
| Editorial implication Both document broad coding-agent tools, but enabled inventories and security configuration vary; verify every required tool in the destination environment. Review scope and limits |
| Filesystem / file modification Repository reads and mutations require the correct workspace and review boundary. | Documented Reads and edits codebase files
| Documented Filesystem tools with confirmation for mutation
| Editorial implication Both establish filesystem operations with controls around mutation; preserve workspace trust, confirmation, and permission expectations during transfer. Review scope and limits |
| Shell / terminal execution Command-heavy automation depends on the target harness's execution controls. | Documented Runs commands through codebase tools
| Documented Shell tools with confirmation and isolation
| Editorial implication Both establish shell execution, but Claude Code permission rules and Gemini CLI confirmation or isolation controls require different operational setup. Review scope and limits |
| Browsing / network access Current external information cannot be assumed available when browsing scope is unestablished. | Not established General browsing not established
| Documented Web tools in official tool reference
| Editorial implication Gemini CLI web tools are documented; general Claude Code browsing is not established. Workflows that need current external data require a fresh target check. Review scope and limits |
| Approvals / permissions Consent, confirmation, and isolation rules determine which delegated actions can proceed. | Documented Deny, ask, allow, and permission modes
| Documented Confirmation, sandbox, and trusted folders
| Editorial implication Claude Code uses deny, ask, and allow rules; Gemini CLI documents confirmation and isolation boundaries. Preserve the destination control vocabulary and policy. Review scope and limits |
| Context scope / inheritance Instructions and tools remain dependable only when their surface, model, and configuration boundaries are preserved. | Documented Managed, user, project, local, and memory scopes
| Documented Global, workspace, just-in-time, and dynamic context
| Editorial implication Both layer project context, but their memory, dynamic substitutions, and configuration boundaries differ; audit effective context before reusing a repository workflow. Review scope and limits |
Criterion-by-criterion interpretation
Scope, limitations, and evidence
Behavior Intelligence supplies the factual answers. Editorial implications remain separate.
01
Open evidence across six products How do AI agents use repository or project instructions?
Why it matters. Repository guidance must be placed in the target agent's documented instruction hierarchy.
Claude Code
DocumentedClaude Code documents managed, user, project, and local CLAUDE.md instruction scopes for coding-agent work.
- Surface
- Claude Code terminal CLI · Claude Code IDE integrations
- Model context
- Not established
- Configuration / version
- Not established
Limits and uncertainty
- The complete default base system prompt is not established.
Gemini CLI
DocumentedGemini CLI documents global, workspace, and just-in-time GEMINI.md files as hierarchical project and task context.
- Surface
- Gemini CLI
- Model context
- Not established
- Configuration / version
- Not established
Limits and uncertainty
- The context hierarchy is distinct from the replaceable built-in system prompt.
02
Open evidence across six products Does the product document memory or persistent context?
Why it matters. Durable workflow context should not be assumed to persist across agent environments.
Claude Code
DocumentedClaude Code documents repository-scoped auto memory that stores selected learnings separately from human-authored CLAUDE.md instructions.
- Surface
- Claude Code terminal CLI · Claude Code IDE integrations
- Model context
- Not established
- Configuration / version
- Not established
Limits and uncertainty
- Auto memory is context, not hard policy enforcement.
Gemini CLI
Not establishedThe selected Gemini CLI tools reference names memory among its categories, but does not establish enough persistence or scope behavior for this question.
- Surface
- Not established
- Model context
- Not established
- Configuration / version
- Not established
Limits and uncertainty
- A tool category alone is not treated as proof of cross-session persistence.
No source link is attached because the reviewed evidence does not establish this answer.
03
Open evidence across six products How is planning or work decomposition documented?
Why it matters. Planning assumptions shape how teams structure, review, and resume multi-step work.
Claude Code
Not establishedThe selected Claude Code sources establish coding tools, instructions, memory, and permissions, but not a specific planning procedure.
- Surface
- Not established
- Model context
- Not established
- Configuration / version
- Not established
Limits and uncertainty
- General agentic coding capability is not treated as evidence of one planning behavior.
No source link is attached because the reviewed evidence does not establish this answer.
Gemini CLI
DocumentedThe selected Gemini CLI tools reference includes planning among the documented tool categories available to the CLI.
- Surface
- Gemini CLI
- Model context
- Not established
- Configuration / version
- Not established
Limits and uncertainty
- The selected evidence does not establish one fixed planning sequence across configurations.
04
Open evidence across six products What tools or tool-calling capabilities are documented?
Why it matters. A portable workflow must use only the tools established by the selected evidence.
Claude Code
DocumentedClaude Code documents tools for reading code, editing files, running commands, and connecting to external tools.
- Surface
- Claude Code terminal CLI · Claude Code IDE integrations
- Model context
- Not established
- Configuration / version
- Permission rules and modes can constrain tool execution.
Limits and uncertainty
- The selected evidence does not establish that every deployment exposes every external tool.
Gemini CLI
DocumentedGemini CLI's selected official reference covers filesystem, execution, planning, memory, MCP, and web tool categories.
- Surface
- Gemini CLI
- Model context
- Not established
- Configuration / version
- Enabled tools and security posture can vary with configuration.
Limits and uncertainty
- The selected evidence does not establish one immutable tool set.
05
Open evidence across six products Can the agent read or modify files?
Why it matters. Repository reads and mutations require the correct workspace and review boundary.
Claude Code
DocumentedClaude Code's official overview says the product reads code, edits files, and runs commands.
- Surface
- Claude Code terminal CLI · Claude Code IDE integrations
- Model context
- Not established
- Configuration / version
- Permission rules distinguish read-only and mutating actions.
Limits and uncertainty
- Access remains bounded by the client environment and configured permissions.
Gemini CLI
DocumentedGemini CLI documents filesystem tools, with mutating file operations subject to confirmation and configured security boundaries.
- Surface
- Gemini CLI
- Model context
- Not established
- Configuration / version
- Sandbox and trusted-folder settings can change the execution boundary.
Limits and uncertainty
- Tool availability varies by configuration and version.
06
Open evidence across six products Can the agent execute shell or terminal commands?
Why it matters. Command-heavy automation depends on the target harness's execution controls.
Claude Code
DocumentedClaude Code's official overview documents command execution as part of codebase operations.
- Surface
- Claude Code terminal CLI
- Model context
- Not established
- Configuration / version
- Permission rules and modes determine when command execution is allowed or asks for approval.
Limits and uncertainty
- The exact command environment is deployment-specific.
Gemini CLI
DocumentedGemini CLI documents shell execution tools whose requests pass through confirmation and configured security policies.
- Surface
- Gemini CLI
- Model context
- Not established
- Configuration / version
- Sandboxing and trusted-folder settings can constrain execution.
Limits and uncertainty
- The enabled tool set is configuration-dependent.
07
Open evidence across six products Can the product browse or access web and network resources?
Why it matters. Current external information cannot be assumed available when browsing scope is unestablished.
Claude Code
Not establishedThe selected Claude Code sources mention external-tool connections but do not establish a general browsing mechanism for this question.
- Surface
- Not established
- Model context
- Not established
- Configuration / version
- Not established
Limits and uncertainty
- External integrations are not treated as equivalent to web browsing.
No source link is attached because the reviewed evidence does not establish this answer.
Gemini CLI
DocumentedGemini CLI's selected official tools reference includes web capabilities among the available tool categories.
- Surface
- Gemini CLI
- Model context
- Not established
- Configuration / version
- Availability depends on enabled tools and security configuration.
Limits and uncertainty
- The selected evidence does not establish unrestricted network access.
08
Open evidence across six products What approval or permission controls are documented?
Why it matters. Consent, confirmation, and isolation rules determine which delegated actions can proceed.
Claude Code
DocumentedClaude Code documents deny, ask, and allow rules with precedence, plus permission modes that constrain tool execution.
- Surface
- Claude Code terminal CLI · Claude Code IDE integrations
- Model context
- Not established
- Configuration / version
- Rules can be managed at different settings scopes and by the client environment.
Limits and uncertainty
- The selected evidence does not establish every deployment policy.
Gemini CLI
DocumentedGemini CLI documents confirmation for mutating file and shell tools, with sandboxing and trusted-folder boundaries.
- Surface
- Gemini CLI
- Model context
- Not established
- Configuration / version
- Security policy and isolation settings shape the actual boundary.
Limits and uncertainty
- The selected evidence does not establish every enterprise policy.
09
Open evidence across six products How is context scoped or inherited across products and agents?
Why it matters. Instructions and tools remain dependable only when their surface, model, and configuration boundaries are preserved.
Claude Code
DocumentedClaude Code documents managed, user, project, and local CLAUDE.md scopes plus separate repository-scoped auto memory.
- Surface
- Claude Code terminal CLI · Claude Code IDE integrations
- Model context
- Not established
- Configuration / version
- The reviewed evidence covers terminal and IDE-oriented product surfaces with a selectable Claude model.
Limits and uncertainty
- The complete default system prompt is not established.
Gemini CLI
DocumentedGemini CLI documents global, workspace, and just-in-time GEMINI.md context plus dynamic injection of enabled skills, subagents, and tools.
- Surface
- Gemini CLI
- Model context
- Not established
- Configuration / version
- The product uses a configurable Gemini model and can fully replace its built-in system prompt.
Limits and uncertainty
- No single immutable runtime assembly is claimed.
Workflow guidance
Migration considerations
These implications follow from the reviewed criteria. They do not express a product preference.
Translate instruction hierarchy
Map CLAUDE.md scopes to the appropriate GEMINI.md hierarchy, or the reverse, without assuming identical inheritance.
Make planning and persistence requirements explicit
Gemini CLI planning and Claude Code auto memory are documented asymmetrically; specify both the plan artifact and durable context requirements.
Carry the destination control model
Filesystem and shell workflows must honor Claude Code permission rules or Gemini CLI confirmation and isolation rather than a generic approval assumption.
Recheck network-dependent steps
Gemini CLI web tools are documented; general Claude Code browsing is not established. Verify external-data dependencies before migration.
Comparison-specific evidence
Differences in available evidence
Claude Code and Gemini CLI combine model context, project instructions, tools, and harness controls in different ways. Their official documentation differs most clearly in base-prompt handling, dynamic assembly, and project-context scope. The analysis below adds prompt and product context to the shared behavior criteria.
- 01
Gemini CLI documents prompt export and replacement
Gemini CLI exposes workflows to export its current built-in prompt and completely replace it. No equivalent full-prompt workflow is established for Claude Code in the selected sources.
- 02
Both document hierarchical project context
Claude Code uses scoped CLAUDE.md files; Gemini CLI uses global, workspace, and just-in-time GEMINI.md context.
- 03
Dynamic context works differently
Claude Code documents repository auto memory. Gemini CLI documents dynamic substitution of skills, subagents, and enabled tools into custom prompts.
Source-specific detail
Product and prompt evidence
These criteria cover prompt visibility, product identity, and other evidence specific to this comparison.
| Criterion | Claude Code | Gemini CLI |
|---|---|---|
| Product and model roleEditorial interpretation. Both are coding-agent harnesses with a selectable or configurable model rather than one product-equals-model identity. | documented Claude Code spans terminal, IDE, desktop, and web surfaces with a separately selected Claude model. | documented Gemini CLI is an open-source terminal agent whose configured Gemini model is separate from its instruction assembly. |
| Base-prompt handlingEditorial interpretation. Official Gemini CLI documentation exposes a prompt workflow that the selected Claude Code documentation does not establish. | not established The selected official sources do not publish or expose a complete default Claude Code system prompt. | documented GEMINI_WRITE_SYSTEM_MD can export the current built-in prompt, while GEMINI_SYSTEM_MD can replace it completely. |
| Project instructionsEditorial interpretation. Both products document hierarchical instruction files, but the filenames and scope models differ. | documented CLAUDE.md instructions can be managed, user-scoped, project-scoped, or local. | documented GEMINI.md context can load globally, from a workspace hierarchy, and just in time from relevant directories. |
| Dynamic instruction assemblyEditorial interpretation. Gemini CLI's selected docs are more explicit about named dynamic substitutions; Claude Code's selected docs focus on scoped files and memory. | documented Claude Code assembles scoped CLAUDE.md context and repository memory, but this source set does not establish an equivalent named substitution template. | documented Custom prompts can substitute available skills, subagents, and enabled tool names, making the resolved prompt configuration-dependent. |
| Tools and permission boundariesEditorial interpretation. Both harnesses mediate agent actions outside model text, with different documented rule vocabularies. | documented Claude Code documents code, file, command, and external-tool operations plus deny, ask, and allow permission rules. | documented Gemini CLI documents filesystem, execution, planning, memory, MCP, and web tools with confirmation and sandbox boundaries. |
| Persistent memoryEditorial interpretation. Claude Code documents a repository-scoped auto-memory store. The selected Gemini CLI source names a memory tool but does not establish an equivalent automatic store. | documented Auto memory stores selected learnings separately from human-authored CLAUDE.md instructions. | not established The selected Gemini CLI tools reference includes memory capability, but does not establish an equivalent repository auto-memory mechanism. |
Using the evidence
How to read this evidence
Choose the evidence boundary before comparing prompts
Gemini CLI supports explicit export and replacement claims; Claude Code's selected sources support architecture analysis without a complete default-prompt claim.
Map repository guidance by scope
Both products support persistent project context, but CLAUDE.md and GEMINI.md have different documented hierarchies and should not be treated as interchangeable names.
Separate prompt assembly from enforcement
Dynamic substitutions and instruction files shape context; tool confirmations, permission rules, and sandboxing shape what actions proceed.
Primary-source trail
Sources used in this comparison
Each source links to its product evidence, with provenance and publication limits preserved.
Claude Code
- Tier A · vendor-publishedClaude Code overview
- Tier A · vendor-publishedHow Claude remembers your project
- Tier A · vendor-publishedClaude Code permissions
Gemini CLI
- Tier A · vendor-publishedGemini CLI system-prompt override documentation
- Tier A · vendor-publishedGemini CLI GEMINI.md context documentation
- Tier A · vendor-publishedGemini CLI tools reference
Deeper cross-agent context
Behavior questions in this comparison
Open the six-product answer for broader evidence and scope.
Repository / project instructionsHow do AI agents use repository or project instructions?Memory / persistent contextDoes the product document memory or persistent context?Planning / work decompositionHow is planning or work decomposition documented?Tools / tool callingWhat tools or tool-calling capabilities are documented?Filesystem / file modificationCan the agent read or modify files?Shell / terminal executionCan the agent execute shell or terminal commands?Browsing / network accessCan the product browse or access web and network resources?Approvals / permissionsWhat approval or permission controls are documented?Context scope / inheritanceHow is context scoped or inherited across products and agents?
Continue comparing