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.
De-duplicated by session_meta.session_id; 44 active rollout log files are tracked separately.
Verified from terminal outcomes; operations are not independent feature units.
Unique paths in successful patch-application records.
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.
- Mon Jul 63
- Tue Jul 71
- Wed Jul 82
- Thu Jul 97
- Fri Jul 106
- Sat Jul 114
- Sun Jul 121
Each count is a de-duplicated session start assigned to that local calendar day.
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.
Patch Churn By Repository
Added plus removed lines recorded in patch inputs.
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
Top-level | Outside git metadata
Top-level | Outside git metadata
Top-level | shopify-headless
Top-level | Outside git metadata
Top-level | shopify-headless
File Touch Mix
Verified Delivery Ledger
Outcomes come from terminal return records. Intent-only command counts remain in the technical appendix.
Command Outcomes
Repositories In Successful Push Output
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.
- 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.
Tool Providers
Completed MCP provider calls, grouped by server namespace.
Skills
Explicitly requested or loaded skills; application is not inferred.
Technical Telemetry
Raw tool, event, workspace, and patch diagnostics used to audit the analyzer. These counts are intentionally secondary to outcomes.
Tool Surfaces
Function Calls
Custom Tool Calls
Specific custom calls and their share of all recorded tool events.