Codex Weekly Usage — June 29–July 5, 2026
A cross-system delivery week centered on Family Shapes and Shopify Headless: terminal outcomes verify delivery to both repositories, while observed Google Workspace, Gmail, Vercel, Shopify, browser, and creative-tool activity shows a broader operating stack. Chronicle context is unavailable for this window and is treated as a source-coverage gap.
De-duplicated by session_meta.session_id; 40 active rollout log files are tracked separately.
Verified from terminal outcomes; operations are not independent feature units.
Unique paths in successful patch-application records.
family-shapes-cannonical 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 Jun 294
- Tue Jun 307
- Wed Jul 15
- Thu Jul 26
- Fri Jul 35
- Sat Jul 40
- Sun Jul 51
Each count is a de-duplicated session start assigned to that local calendar day.
Total: 8,818 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
Family Shapes held the largest resolved tool share at 4,420 calls (50.1%), followed by Shopify Headless at 3,407 (38.6%). Faire Lead Ops contributed a smaller resolved activity trace, while 701 calls (7.9%) remained outside git metadata and must not be reassigned to a repository. Terminal output verifies delivery for Family Shapes and Shopify Headless only; the other repository and projectless records are activity evidence, not delivery claims.
Output Shape
Compare the rollouts carrying the largest patches with the mix of file categories touched.
Patch Churn By Rollout
Top-level | shopify-headless
Top-level | family-shapes-cannonical
Top-level | shopify-headless
Top-level | family-shapes-cannonical
Top-level | Outside git metadata
Top-level | family-shapes-cannonical
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
Terminal outcomes record 70 successful commit operations, 63 successful content pushes, 122 successful pull-request operations, and 7 successful branch-cleanup pushes. The evidence also retains 2 pending content pushes, 51 pending pull-request operations, 25 pull-request failures, 6 commit failures, and 1 branch-cleanup push failure, so attempted operations are not promoted to blanket success. Operation counts, file touches, and patch churn describe verification and output composition; they are not independent feature units or productivity measures.
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.