codex usage

    Codex Weekly Usage — August 3–9, 2026

    An integration-heavy week paired Hyphenomenon publishing and design work with sustained multi-mailbox operations and Shopify delivery: 34 de-duplicated sessions across 82 active rollout logs, verified delivery traces for four repositories, and a Friday–Saturday model-context concentration that accounted for 63.5% of processed tokens.

    Template-generated · Analyzer: codex-usage-report-v6 · Model: gpt-5.6-sol · high

    ~4B
    Tokens processed

    Input plus output tokens in retained local Codex telemetry; includes cached input and is not a cost or productivity score.

    35
    Top-level tasks

    Top-level rollout files active in the window; delegated rollouts are counted separately.

    47
    Delegated rollouts

    Subagent or spawned-thread rollout files with timestamped activity in the window.

    1,216
    Turns

    Recorded turn contexts across top-level and delegated rollouts; not elapsed work time.

    Token Usage

    Cumulative runtime counters are differenced per rollout. Repeated snapshots are ignored; cached input stays visible instead of being mistaken for fresh context.

    Token Usage

    Retained local Codex telemetry only; not an account-wide usage or billing statement.

    3,889,947,692
    Total processed
    Input + output
    Input
    3,879,675,815
    Cached input
    3,763,420,544
    Non-cached input
    116,255,271
    Output
    10,271,877
    Reasoning output
    3,051,301

    Cached input is 97% of input. Reasoning output is included within output tokens.

    Tokens By Day

    Processed input plus output assigned to the local day of each positive cumulative-counter increment.

    Fri Aug 71,449,216,207 37%
    Sat Aug 81,020,808,414 26%
    Mon Aug 3413,906,161 11%
    Sun Aug 9307,686,613 8%
    Thu Aug 6303,124,576 8%
    Tue Aug 4247,582,314 6%
    Wed Aug 5147,623,407 4%

    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 Aug 313
    2. Tue Aug 42
    3. Wed Aug 51
    4. Thu Aug 64
    5. Fri Aug 77
    6. Sat Aug 84
    7. Sun Aug 93

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

    Clock-hour pattern across the full week
    12 AM
    3
    495
    6c
    2 AM
    888
    10c
    1,038
    9c
    4 AM
    294
    9c
    754
    16c
    6 AM
    671
    9c
    1,082
    23c
    8 AM
    1,927
    19c
    1,077
    9c
    10 AM
    1,774
    14c
    1,975
    25c
    12 PM
    1,601
    18c
    1,434
    14c
    2 PM
    977
    8c
    689
    11c
    4 PM
    804
    8c
    396
    6c
    6 PM
    286
    3c
    18
    8 PM
    16
    16
    10 PM

    Total: 18,215 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.

    hyphenomenon9,864 54%
    shopify-headless4,619 25%
    multi-mailbox-ops3,530 19%
    Outside git metadata188 1%
    maggie-todo14 <1%

    Output Shape

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

    File Touch Mix

    5,053touches
    Docs and governance2,80556%
    Application and pipeline code1,79636%
    Other files4208%
    Config and automation32<1%

    Verified Delivery Ledger

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

    Command Outcomes

    Pull request operations - unknown
    Count323
    Share39%
    Commit operations - success
    Count217
    Share26%
    Content push operations - success
    Count166
    Share20%
    Commit operations - unknown
    Count52
    Share6%
    Content push operations - unknown
    Count19
    Share2%
    Pull request operations - success
    Count16
    Share2%
    Branch cleanup pushes - success
    Count15
    Share2%
    Other
    Count12
    Share1%

    Repositories In Successful Push Output

    hyphenomenon
    Count1
    Share25%
    multi-mailbox-ops
    Count1
    Share25%
    rps-digital
    Count1
    Share25%
    shopify-headless
    Count1
    Share25%

    Agent Stack Used

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

    App or connectorFigma
    Runtime providerMulti Mailbox Ops
    Loaded skillmulti-mailbox-ops
    • 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.

    Figma
    Invoked8 rollouts
    932
    Vercel
    Invoked12 rollouts
    423
    Shopify
    Invoked3 rollouts
    127
    Resend
    Invoked1 rollout
    30
    Google Drive
    Invoked1 rollout
    26
    GitHub
    Invoked10 rollouts
    22
    Neon Postgres
    Invoked1 rollout
    4
    Gmail
    Invoked3 rollouts
    3

    Tool Providers

    Completed MCP provider calls, grouped by server namespace.

    Multi Mailbox Ops
    Invoked4 rollouts
    2,209
    Node tool runtime
    Invoked24 rollouts
    1,742
    Playwright browser
    Invoked3 rollouts
    312
    OpenaiDeveloperDocs
    Invoked6 rollouts
    49
    Shopify Dev Mcp
    Invoked2 rollouts
    21

    Skills

    Explicitly requested or loaded skills; application is not inferred.

    multi-mailbox-ops
    Loaded11 rollouts
    212
    control-in-app-browser
    Loaded + Requested13 rollouts
    55
    audit
    Loaded + Requested10 rollouts
    35
    figma-use
    Loaded3 rollouts
    35
    visual-design-critique
    Requested24 rollouts
    34
    user-context
    Loaded + Requested10 rollouts
    33
    catalog-review
    Loaded12 rollouts
    30
    index
    Loaded + Requested5 rollouts
    28
    playwright
    Loaded + Requested10 rollouts
    26
    control-chrome
    Loaded7 rollouts
    25

    Chronicle Context Across The Week

    These panels are calculated directly from persisted Chronicle summaries. Lane counts overlap and are not duration.

    Open source reportChronicle Daily Report — August 5, 2026

    Work Lane Mentions

    Planning and knowledge work441 30%
    Software and repo delivery385 26%
    Storefront and catalog work358 24%
    Print and artwork production185 13%
    Wholesale and shipping104 7%

    Evidence Coverage

    Screenshot citations
    Count4,244
    Share68%
    Unique cited minutes
    Count1,433
    Share23%
    Overlapping 10-minute summaries
    Count507
    Share8%
    Observed clock hours
    Count17
    Share<1%

    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 shell15,947 88%
    Long-running task waits1,501 8%
    Multi-agent tools762 4%
    Other/uncategorized5 <1%

    Function Calls

    1,501
    437
    169
    53
    48
    46
    9
    5
    wait
    wait_agent
    send_message
    followup_task
    list_agents
    spawn_agent
    interrupt_agent
    request_user_input

    Custom Tool Calls

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

    exec
    Count15,947
    Share88%

    Response Events

    response_item
    Count60,678
    Share49%
    event_msg
    Count59,625
    Share48%
    turn_context
    Count1,216
    Share<1%
    session_meta
    Count871
    Share<1%
    world_state
    Count621
    Share<1%
    inter_agent_communication_metadata
    Count355
    Share<1%
    compacted
    Count216
    Share<1%

    Patch Applications

    Successful patch applications
    Count2,507
    Share100%

    Output Records

    Tool output records
    Count17,993
    Share84%
    Git refs in output
    Count2,446
    Share11%
    Truncated outputs
    Count690
    Share3%
    GitHub PR links emitted
    Count297
    Share1%
    Long-running command handoffs
    Count2
    Share<1%

    Session And Log Audit

    Raw session_meta records
    Count871
    Share88%
    Active rollout log files
    Count82
    Share8%
    Unique session_meta.session_id values
    Count34
    Share3%

    Token Counter Audit

    28,608
    28,235
    373
    Token-count records
    Metered model-response increments
    Repeated snapshots ignored

    Source Coverage

    96
    82
    2
    Candidate rollout files inspected
    Active rollout files
    Configured local session stores