Codex Weekly Usage Report — September 7–13, 2026
Executive summary
Rock Paper Scissors review and operations led the observed September 7–13 week.
Available Skysight evidence across five days contains 60 active public summaries across six work arcs, led by Rock Paper Scissors operations. Review and quality assurance is the strongest work-mode signal, followed by operations and fulfillment. The record includes pick-list preparation and broader delivery and review signals; three follow-up categories remain open. September 9 and 12 have no available Skysight evidence, so their activity remains unknown.
Codex execution telemetry is supporting evidence, not a measure of productivity, duration, or the week's value.
Distinct public work threads supported by retained Skysight summaries.
Public-safe outcomes or decisions supported by observed context.
Follow-ups the observed record does not show as resolved.
Top-level Codex tasks recorded in local execution logs; not a productivity score.
What shaped the week
Major work arcs
Rock Paper Scissors operations and Other observed work are the two largest observed arcs by retained summary mentions. Counts can overlap and do not represent duration.
Observed evidence by work arc
Retained structured-summary mentions; overlapping evidence, not time allocation.
Rock Paper Scissors operations
33 observedCatalog quality review and wholesale or fulfillment preparation.
Other observed work
17 observedObserved work that did not match a named public reporting arc.
Hyphenomenon product and reporting
5 observedProduct-system review, reporting strategy, and project sequencing.
3 additional work arcsLower-volume observed threads remain available without competing with the primary arcs.
Product strategy
5 observedProduct framing, research, and strategic decision-making.
Research and administration
4 observedResearch, purchasing, and administrative follow-through.
Mailbox and customer operations
2 observedMailbox, customer-support, and operational follow-through.
Outcomes and decisions
Faire fulfillment input prepared
AdvancedPrepared the pick-list input for a size-counting and fulfillment task.
Delivery and implementation progress
AdvancedRetained summaries indicate implementation, publication, deployment, or other delivery progress.
Review and verification decision
AdvancedRetained summaries indicate an approval, acceptance, verification, or passed review gate.
Next steps and open loops
Pick-list size totals
OpenComplete and verify the size totals requested from the Faire pick list.
Outstanding follow-through
OpenRetained summaries identify work that remained pending or still needed follow-through.
Unresolved quality or reliability issue
OpenRetained summaries identify an unresolved issue, defect, failure, or remediation need.
How the observed week unfolded5 day summaries
Sep 7
Rock Paper Scissors operations + Other observed work
20 active summaries, led by review and quality assurance signals. 1 additional observed summary was protected.
Sep 8
Rock Paper Scissors operations + Other observed work
8 active summaries, led by operations and fulfillment signals.
Sep 10
Other observed work + Product strategy
9 active summaries, led by review and quality assurance signals. 2 additional observed summaries were protected.
Sep 11
Rock Paper Scissors operations + Hyphenomenon product and reporting
20 active summaries, led by review and quality assurance signals.
Sep 13
Other observed work + Rock Paper Scissors operations
3 active summaries, led by research and administration signals.
How to read this evaluationWork-mode signals, protected context, and evidence limits
Observed work-mode signals
Overlapping summary-level signals, not duration or a complete time sheet.
Privacy and evidence boundary
3 observed summaries were excluded from public topic analysis. Their time positions remain visible so the report does not mislabel protected context as missing or inactive.
This evaluation uses 75 summaries from five isolated Skysight source-contract v2 remote restores, each hash-verified with zero conflicts or disappeared records. September 9 and 12 are missing and unverified. Three protected positions remain visible without exposing topics; capture completeness is not asserted. Counts are overlapping evidence signals rather than duration, productivity, value, or unique task totals. Uncovered intervals remain unknown rather than zero activity; retained local Codex telemetry excludes other-device or cloud-only activity absent from those logs.
Evidence appendix
Repository activity, delivery records, source evidence, and technical diagnostics support the evaluation without competing with its first read.
Explore supporting evidenceExecution, delivery, Skysight source context, and technical telemetry
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.
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
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.
Tool Providers
Completed MCP provider calls, grouped by server namespace.
Skills
Explicitly requested or loaded skills; application is not inferred.
Skysight Evidence Across The Week
This evidence view locates the public work arcs and protected-context positions that support the synthesis. The calendar grid is not expected computer activity, and values are not duration.
Rock Paper Scissors operations
Other observed work
Hyphenomenon product and reporting
Product strategy
Research and administration
Mailbox and customer operations
Protected context
| Work domain | 12–4a | 4–8a | 8a–12p | 12–4p | 4–8p | 8p–12a |
|---|---|---|---|---|---|---|
| Rock Paper Scissors operations | Rock Paper Scissors operations, 12–4a: no retained summary evidence | Rock Paper Scissors operations, 4–8a: 10 summary mentions | Rock Paper Scissors operations, 8a–12p: 14 summary mentions | Rock Paper Scissors operations, 12–4p: 7 summary mentions | Rock Paper Scissors operations, 4–8p: 2 summary mentions | Rock Paper Scissors operations, 8p–12a: no retained summary evidence |
| Other observed work | Other observed work, 12–4a: no retained summary evidence | Other observed work, 4–8a: 2 summary mentions | Other observed work, 8a–12p: 9 summary mentions | Other observed work, 12–4p: 5 summary mentions | Other observed work, 4–8p: 1 summary mention | Other observed work, 8p–12a: no retained summary evidence |
| Hyphenomenon product and reporting | Hyphenomenon product and reporting, 12–4a: no retained summary evidence | Hyphenomenon product and reporting, 4–8a: 1 summary mention | Hyphenomenon product and reporting, 8a–12p: 2 summary mentions | Hyphenomenon product and reporting, 12–4p: 2 summary mentions | Hyphenomenon product and reporting, 4–8p: zero matches within retained summaries | Hyphenomenon product and reporting, 8p–12a: no retained summary evidence |
| Product strategy | Product strategy, 12–4a: no retained summary evidence | Product strategy, 4–8a: 4 summary mentions | Product strategy, 8a–12p: zero matches within retained summaries | Product strategy, 12–4p: zero matches within retained summaries | Product strategy, 4–8p: 1 summary mention | Product strategy, 8p–12a: no retained summary evidence |
| Research and administration | Research and administration, 12–4a: no retained summary evidence | Research and administration, 4–8a: 3 summary mentions | Research and administration, 8a–12p: 1 summary mention | Research and administration, 12–4p: zero matches within retained summaries | Research and administration, 4–8p: zero matches within retained summaries | Research and administration, 8p–12a: no retained summary evidence |
| Mailbox and customer operations | Mailbox and customer operations, 12–4a: no retained summary evidence | Mailbox and customer operations, 4–8a: zero matches within retained summaries | Mailbox and customer operations, 8a–12p: zero matches within retained summaries | Mailbox and customer operations, 12–4p: 2 summary mentions | Mailbox and customer operations, 4–8p: zero matches within retained summaries | Mailbox and customer operations, 8p–12a: no retained summary evidence |
| Protected context | Protected context, 12–4a: no retained summary evidence | Protected context, 4–8a: 1 withheld summary mention | Protected context, 8a–12p: 2 withheld summary mentions | Protected context, 12–4p: zero matches within retained summaries | Protected context, 4–8p: zero matches within retained summaries | Protected context, 8p–12a: no retained summary evidence |
Structured Evidence Coverage
Codex Execution Activity
Token and hourly activity describe the agent execution layer. They are supporting diagnostics, not a measure of the week's value, duration, or human productivity.
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.
- Input
- 316,684,776
- Cached input
- 303,777,152
- Non-cached input
- 12,907,624
- Output
- 1,018,788
- Reasoning output
- 243,625
Cached input is 96% 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.
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 Sep 78
- Tue Sep 84
- Wed Sep 90
- Thu Sep 105
- Fri Sep 113
- Sat Sep 123
- Sun Sep 134
Each count is a de-duplicated session start assigned to that local calendar day.
Total: 2,125 tool calls. “c” marks successful commit operations in that hour.
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.