codex usage

    Codex Weekly Usage — July 6–12, 2026

    A cross-system delivery week in which Codex connected repository work with Google Workspace, Figma, Gmail, and Shopify operations while keeping verified delivery evidence separate from raw activity volume.

    Template-generatedAnalyzer · codex-usage-report-v5Model · Not recorded
    24
    Unique Codex sessions

    De-duplicated by session_meta.session_id; 44 active rollout log files are tracked separately.

    17
    Successful commit operations

    Verified from terminal outcomes; operations are not independent feature units.

    81
    Files touched

    Unique paths in successful patch-application records.

    2
    Repositories delivered

    hyphenomenon and shopify-headless

    Activity By Day And Clock Hour

    The day row shows each date in the report window. The hour chart below combines the same clock hour across all seven days; it is not a single-day timeline.

    Daily session timeline
    1. Mon Jul 63
    2. Tue Jul 71
    3. Wed Jul 82
    4. Thu Jul 97
    5. Fri Jul 106
    6. Sat Jul 114
    7. Sun Jul 121

    Each count is a de-duplicated session start assigned to that local calendar day.

    Clock-hour pattern across the full week
    12 AM
    2 AM
    222
    4 AM
    152
    2c
    182
    1c
    6 AM
    178
    421
    8 AM
    314
    2c
    372
    10 AM
    350
    212
    1c
    12 PM
    194
    298
    2 PM
    146
    4 PM
    52
    442
    6c
    6 PM
    407
    5c
    8 PM
    10 PM

    Total: 3,942 tool calls. “c” marks successful commit operations in that hour.

    Where The Work Landed

    Repository activity and changed lines show which codebases received attention during the report window.

    Tool Calls By Repository

    Working repository resolved from tool workdir or turn context.

    hyphenomenon1,384 35%
    shopify-headless946 24%
    Outside git metadata911 23%
    family-shapes-cannonical658 17%
    faire-lead-ops43 1%

    Patch Churn By Repository

    Added plus removed lines recorded in patch inputs.

    Outside git metadata2,020 68%
    shopify-headless949 32%

    Delivery Extended Beyond One Repository

    hyphenomenon held the largest resolved tool share, followed by shopify-headless and family-shapes-cannonical. Twelve sessions and 911 tool calls remained outside resolved git metadata, so projectless operations must not be reassigned to a repository. Terminal output verifies delivery evidence for hyphenomenon and shopify-headless only.

    Output Shape

    Compare the rollouts carrying the largest patches with the mix of file categories touched.

    Patch Churn By Rollout

    Rollout 17827 28%

    Top-level | Outside git metadata

    Rollout 09696 23%

    Top-level | Outside git metadata

    Rollout 14525 18%

    Top-level | shopify-headless

    Rollout 12497 17%

    Top-level | Outside git metadata

    Rollout 15424 14%

    Top-level | shopify-headless

    File Touch Mix

    356touches
    Application and pipeline code18251%
    Docs and governance15042%
    Other files236%
    Config and automation1<1%

    Verified Delivery Ledger

    Outcomes come from terminal return records. Intent-only command counts remain in the technical appendix.

    Command Outcomes

    Commit operations - success
    Count17
    Share40%
    Content push operations - success
    Count13
    Share30%
    Content push operations - unknown
    Count4
    Share9%
    Commit operations - unknown
    Count2
    Share5%
    Content push operations - pending
    Count2
    Share5%
    Pull request operations - pending
    Count2
    Share5%
    Branch cleanup pushes - pending
    Count1
    Share2%
    Other
    Count2
    Share5%

    Repositories In Successful Push Output

    hyphenomenon
    Count1
    Share50%
    shopify-headless
    Count1
    Share50%

    Verification Was Part Of The Work

    The window produced 17 successful commit operations and 13 successful content-push operations. Four additional push operations lacked a terminal outcome, and two ended in long-running handoffs, so they remain unresolved rather than being promoted to success. Application and pipeline code plus docs and governance dominated recorded file touches; neither commit counts nor patch churn represent independent feature units or productivity.

    Agent Stack Used

    Observed runtime evidence only; the available catalog is excluded. Status chips distinguish completed calls, skill loads, and explicit requests.

    App or connectorGoogle Drive
    Runtime providerNode tool runtime
    Loaded skillgoogle-sheets
    • Invoked means a completed runtime call was recorded.
    • Loaded means a skill file was read or discovered.
    • Requested marks an explicit skill request in the source.
    • The logs do not preserve a reliable causal chain between every layer, so the diagram shows observed layers rather than inventing one.

    Apps and Connectors

    Completed connector calls recorded by the runtime.

    Google Drive
    Invoked13 rollouts
    492
    Figma
    Invoked3 rollouts
    225
    Gmail
    Invoked5 rollouts
    52
    Shopify
    Invoked5 rollouts
    21
    Vercel
    Invoked1 rollout
    16
    Adobe (formerly Photoshop)
    Invoked2 rollouts
    4

    Tool Providers

    Completed MCP provider calls, grouped by server namespace.

    Node tool runtime
    Invoked8 rollouts
    423
    Computer Use
    Invoked1 rollout
    23
    Shopify Dev Mcp
    Invoked1 rollout
    3
    OpenaiDeveloperDocs
    Invoked1 rollout
    2

    Skills

    Explicitly requested or loaded skills; application is not inferred.

    google-sheets
    Loaded9 rollouts
    15
    figma-use
    Loaded2 rollouts
    14
    google-slides
    Loaded9 rollouts
    13
    frontend-app-builder
    Loaded6 rollouts
    10
    verification-before-completion
    Loaded7 rollouts
    10
    subagent-driven-development
    Loaded + Requested5 rollouts
    9
    test-driven-development
    Loaded6 rollouts
    8
    computer-use
    Loaded + Requested4 rollouts
    7
    continue-until-blocked
    Loaded + Requested3 rollouts
    7
    working-modes
    Loaded + Requested3 rollouts
    7

    Technical Telemetry

    Raw tool, event, workspace, and patch diagnostics used to audit the analyzer. These counts are intentionally secondary to outcomes.

    Tool Surfaces

    Terminal/local shell2,932 74%
    Multi-agent tools301 8%
    Google Slides262 7%
    Long-running task waits99 3%
    Google Sheets87 2%
    Local image review84 2%
    Code editing56 1%
    Other121 3%

    Function Calls

    761
    205
    132
    99
    88
    84
    53
    381
    exec_command
    wait_agent
    _get_slide_thumbnail
    wait
    write_stdin
    view_image
    _get_spreadsheet_range
    Other

    Custom Tool Calls

    Specific custom calls and their share of all recorded tool events.

    exec
    Count2,083
    Share53%
    apply_patch
    Count56
    Share1%

    Response Events

    response_item
    Count12,789
    Share56%
    event_msg
    Count9,328
    Share41%
    turn_context
    Count228
    Share1%
    session_meta
    Count135
    Share<1%
    inter_agent_communication_metadata
    Count99
    Share<1%
    world_state
    Count44
    Share<1%
    compacted
    Count16
    Share<1%

    Patch Applications

    Successful patch applications
    Count234
    Share81%
    Apply patch calls
    Count56
    Share19%

    Output Records

    Tool output records
    Count3,894
    Share88%
    Git refs in output
    Count282
    Share6%
    Truncated outputs
    Count133
    Share3%
    Long-running command handoffs
    Count89
    Share2%
    Non-zero terminal exits
    Count34
    Share<1%
    GitHub PR links emitted
    Count17
    Share<1%

    Session And Log Audit

    Raw session_meta records
    Count135
    Share67%
    Active rollout log files
    Count44
    Share22%
    Unique session_meta.session_id values
    Count24
    Share12%