codex usage

    Codex Weekly Usage — July 13–19, 2026

    A concentrated Hyphenomenon delivery week: 29 de-duplicated Codex sessions across 57 rollout logs, an early-week push, a two-day evidence gap, and a weekend return with verified delivery to two repositories.

    Period
    Jul 13, 2026 00:00 EDT to Jul 20, 2026 00:00 EDT
    Generated
    Jul 21, 2026
    Validation
    Passed
    Analyzer
    codex-usage-report-v5
    29
    Unique Codex sessions

    De-duplicated by session_meta.session_id; 57 active rollout log files are tracked separately.

    90
    Successful commit operations

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

    406
    Files touched

    Unique paths in successful patch-application records.

    2
    Repositories delivered

    codex-skills and hyphenomenon

    Executive Summary

    The week formed three distinct phases: 18 de-duplicated Codex sessions started Monday through Wednesday, no session starts or Chronicle summaries were recorded Thursday or Friday, and 11 sessions marked a weekend return. Hyphenomenon was the center of gravity, accounting for 10,798 of 12,251 tool calls (88.1%), while the top three rollout logs carried 51.78% of recorded tool activity. Terminal outcomes verify 90 successful commit operations, 66 successful content-push operations, and delivery output naming Hyphenomenon and codex-skills; those operation counts are evidence of execution, not independent feature units or elapsed effort.

    Activity By Day And Clock Hour

    Unique sessions by local start day, followed by tool calls aggregated by local clock hour across the full window.

    Unique Sessions By Day

    De-duplicated session_meta.session_id values assigned to their recorded local start day.

    Wed Jul 159 31%
    Mon Jul 137 24%
    Sat Jul 186 21%
    Sun Jul 195 17%
    Tue Jul 142 7%
    12 AM
    2 AM
    396
    4c
    204
    3c
    4 AM
    263
    3c
    774
    5c
    6 AM
    916
    5c
    591
    5c
    8 AM
    946
    11c
    668
    3c
    10 AM
    573
    2c
    507
    1c
    12 PM
    2,674
    29c
    210
    2 PM
    415
    3c
    380
    1c
    4 PM
    620
    4c
    258
    3c
    6 PM
    1,641
    8c
    215
    8 PM
    10 PM

    Total: 12,251 tool calls. “c” marks successful commit operations in that hour.

    Activity Concentration

    Session starts peaked on Wednesday (9), with Monday contributing 7, Tuesday 2, Saturday 6, and Sunday 5. The 1 PM and 7 PM local clock-hour buckets together contained 4,315 of 12,251 tool calls (35.22%) across the week. The Thursday-Friday gap appears in both Codex session starts and Chronicle summaries, but it proves only an evidence gap in these sources, not inactivity.

    Where The Work Landed

    Tool volume and patch churn answer different questions, so they are shown side by side instead of collapsed into one repo count.

    Tool Calls By Repository

    Working repository resolved from tool workdir or turn context.

    hyphenomenon10,798 88%
    Outside git metadata1,352 11%
    shopify-headless71 1%
    bpe-marketing-lp15 0%
    codex-skills13 0%
    shopify-ai-product-optimizer2 0%

    Patch Churn By Repository

    Added plus removed lines in patch inputs. Diagnostic only, not a productivity score.

    hyphenomenon9,730 68%
    Outside git metadata4,524 32%

    Delivery Extended Beyond One Repository

    Hyphenomenon dominated resolved tool activity, but it was not the whole operating surface. Another 1,352 tool calls (11%) occurred outside resolved git metadata, and smaller command-level traces resolved to shopify-headless, bpe-marketing-lp, codex-skills, and shopify-ai-product-optimizer. Only Hyphenomenon and codex-skills appear in successful push output, so the other repository labels are activity evidence rather than delivery claims.

    Output Was Concentrated

    A small number of rollouts carried most patch churn, while file touches skewed toward documentation and governance work.

    Patch Churn By Rollout

    Rollout 402,910 20%

    Top-level | Outside git metadata

    Rollout 302,476 17%

    Top-level | hyphenomenon

    Rollout 392,340 16%

    Top-level | hyphenomenon

    Rollout 482,078 15%

    Top-level | hyphenomenon

    Rollout 531,892 13%

    Top-level | hyphenomenon

    Rollout 34783 5%

    Top-level | Outside git metadata

    Other1,775 12%

    File Touch Mix

    2,029touches
    Docs and governance1,23861%
    Application and pipeline code65432%
    Other files925%
    Config and automation231%
    Report prototypes221%

    Output Shape

    Repeated file-touch records leaned toward documentation and governance (1,238) over application and pipeline code (654), with 406 unique patched paths across the week. That pattern fits a week centered on intake, report infrastructure, review packets, and delivery governance, while still carrying implementation work. Touch and patch counts can repeat paths and reflect analyzer mechanics; they describe output composition, not volume produced or productivity.

    Verified Delivery Ledger

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

    Command Outcomes

    Commit operations - success
    Count90
    Share31%
    Content push operations - success
    Count66
    Share23%
    Pull request operations - success
    Count61
    Share21%
    Pull request operations - unknown
    Count28
    Share10%
    Content push operations - unknown
    Count12
    Share4%
    Commit operations - unknown
    Count9
    Share3%
    Pull request operations - pending
    Count9
    Share3%
    Other
    Count16
    Share5%

    Repositories In Successful Push Output

    codex-skills
    Count1
    Share50%
    hyphenomenon
    Count1
    Share50%

    Verification Was Part Of The Work

    Terminal outcomes record 90 successful commit operations, 66 successful content pushes, 61 successful pull-request operations, and 6 successful branch-cleanup pushes. The evidence also retains 12 content pushes with unknown outcomes, 3 pending pushes, 28 pull-request operations with unknown outcomes, 9 pending pull-request operations, and 4 failures. Successful operations are verified outcomes, but the unresolved tail prevents a claim that every attempted delivery completed cleanly.

    Agent Stack Used

    Observed invocations only. Available tools are excluded; skill rows distinguish an explicit request from an observed SKILL.md load.

    Apps and Connectors

    Completed connector calls recorded by the runtime.

    Vercel
    Invoked | 10 rollouts
    449
    Figma
    Invoked | 5 rollouts
    250
    Google Drive
    Invoked | 5 rollouts
    87
    Shopify
    Invoked | 2 rollouts
    49
    Gmail
    Invoked | 5 rollouts
    44
    GitHub
    Invoked | 1 rollout
    1

    Tool Providers

    Completed MCP provider calls, grouped by server namespace.

    Node tool runtime
    Invoked | 15 rollouts
    1,263
    Playwright browser
    Invoked | 8 rollouts
    320
    Shopify Dev Mcp
    Invoked | 1 rollout
    4

    Skills

    Explicitly requested or loaded skills; application is not inferred.

    gmail
    Loaded | 5 rollouts
    45
    frontend-app-builder
    Loaded | 5 rollouts
    36
    control-in-app-browser
    Loaded | 9 rollouts
    33
    hyphenomenon-project-intake
    Loaded | 9 rollouts
    30
    playwright
    Loaded | 11 rollouts
    30
    hyphenomenon-chat-intake
    Loaded | 7 rollouts
    23
    subagent-driven-development
    Loaded + Requested | 8 rollouts
    22
    continue-until-blocked
    Loaded + Requested | 5 rollouts
    21
    project-lifecycle
    Loaded | 7 rollouts
    21
    using-git-worktrees
    Loaded | 5 rollouts
    20

    Agent Stack Evidence

    Completed connector calls were led by Vercel (449) and Figma (250), followed by Google Drive (87), Shopify (49), Gmail (44), and GitHub (1). Completed MCP provider calls were concentrated in the Node tool runtime (1,263) and Playwright browser (320), with 4 Shopify Dev MCP calls. Skill rows include only explicit requests or literal SKILL.md loads; gmail, frontend-app-builder, control-in-app-browser, hyphenomenon-project-intake, and playwright were the most frequently observed labels, but a load does not prove the skill was applied.

    Chronicle Context Across The Week

    Chronicle supplies contextual coverage across desktop work. Lane counts overlap and should not be summed as duration.

    Work Lane Mentions

    Planning and knowledge work400 26%
    Software and repo delivery345 23%
    Print and artwork production323 21%
    Storefront and catalog work316 21%
    Wholesale and shipping145 9%

    Evidence Coverage

    Screenshot citations
    Count3,905
    Share71%
    Unique cited minutes
    Count1,092
    Share20%
    Overlapping 10-minute summaries
    Count450
    Share8%
    Observed clock hours
    Count18
    Share0%

    Chronicle Context

    Chronicle contributes 450 overlapping ten-minute summaries, 3,905 citation occurrences, and 1,092 unique cited minutes across 18 observed clock hours. Planning and knowledge work appeared in 400 summaries, software and repo delivery in 345, print and artwork production in 323, storefront and catalog work in 316, and wholesale or shipping in 145. The overlap shows a mixed operating week beyond repository work; the lane totals must not be summed as duration, and the missing Thursday-Friday summaries remain an explicit coverage limitation.

    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 shell10,192 83%
    Multi-agent tools1,012 8%
    Long-running task waits522 4%
    Code editing307 3%
    Local image review68 1%
    Planning/status39 0%
    Vercel29 0%
    Other82 1%

    Function Calls

    2,940
    731
    522
    184
    123
    68
    58
    250
    exec_command
    wait_agent
    wait
    write_stdin
    send_message
    view_image
    spawn_agent
    Other

    Custom Tool Calls

    exec
    Count7,068
    Share96%
    apply_patch
    Count307
    Share4%

    Response Events

    response_item
    Count39,162
    Share56%
    event_msg
    Count29,809
    Share42%
    turn_context
    Count490
    Share1%
    session_meta
    Count248
    Share0%
    inter_agent_communication_metadata
    Count214
    Share0%
    world_state
    Count209
    Share0%
    compacted
    Count96
    Share0%

    Patch Applications

    Successful patch applications
    Count1,155
    Share79%
    Apply patch calls
    Count307
    Share21%

    Output Records

    Tool output records
    Count12,100
    Share81%
    Git refs in output
    Count1,702
    Share11%
    Truncated outputs
    Count645
    Share4%
    Long-running command handoffs
    Count205
    Share1%
    Non-zero terminal exits
    Count139
    Share1%
    GitHub PR links emitted
    Count130
    Share1%

    Session And Log Audit

    Raw session_meta records
    Count248
    Share74%
    Active rollout log files
    Count57
    Share17%
    Unique session_meta.session_id values
    Count29
    Share9%

    Anomalies And Uncertainty

    The source contains 248 raw session_meta records but only 29 unique session_meta.session_id values across 57 active rollout log files; the report uses the de-duplicated session count and exposes the other two figures only as audit fields. Tool, patch, and file-touch telemetry can repeat across retained rollout histories, while delivery operations are keyed to terminal call outcomes. Truncated outputs (645), long-running handoffs (205), and non-zero terminal exits (139) are retained as diagnostic signals and are not treated as proof of failed work, duration, or productivity.