usage-report
Skill1 starsChanged 56 days agoMITView on GitHub
Use when measuring recorded local usage for an explicit date range or merging device reports while preserving unknown coverage, cached-input subsets and reasoning-output subsets.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- agentic-community/mcp-gateway-registrytheir own version, first seen Nov 6, 2026
- CheehooLabs/SpureeSkillstheir own version, first seen Nov 1, 2026
- artisansplatform/claude-code-usagetheir own version, first seen Oct 4, 2026
- reganomika/Bullpentheir own version, first seen Jul 21, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- agentic-community/mcp-gateway-registry★ 1ksame name
- CheehooLabs/SpureeSkills★ 18same name
- artisansplatform/claude-code-usage★ 2same name
- reganomika/Bullpen★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- batch-statusSkill
- compact-outputSkill
- issue-adminSkill
- luna-submitSkill
- repo-lookupSkill
- run-checksSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use the local collector only with an identified log file/directory and device label.
- Very specific: line 25
Read coverage, deduplication, totals, automatic_approval, warnings and the report evidence path.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Local usage reports
Use the local collector only with an identified log file/directory and device
label. It reads JSONL/JSON/log records; it does not access provider accounts,
estimate missing usage or publish prompts. The input source defaults to
~/.codex/sessions only when the parent has not supplied one.
python scripts/token_saver.py usage --start 2026-09-01 --end 2026-09-07 --utc-offset 8 --device laptop --input <log-dir> --output <report.json>
python scripts/token_saver.py usage-merge --inputs laptop.json desktop.json --output all-devices.jsonTimestamps must be timezone-aware; malformed or naive records remain unknown. The end date is inclusive in the request and is returned as an explicit
half-open interval [start, end_exclusive). Records are deduplicated by
response ID across every source date before that interval is filtered. Cached
input is included within input tokens; reasoning output is included within
output tokens and is reported as a subset. Records marked automatic approval
are counted separately from normal totals.
Read coverage, deduplication, totals, automatic_approval, warnings and
the report evidence path. Missing logs, unreadable files and unknown coverage
remain blocked/unknown; never render them as zero. Mixed formats produce a
warning. --hash-receipts stores SHA-256 response receipts without IDs or
prompts, but receipts cannot prove a physical device or repair cross-device
duplicates.
usage-merge validates schema, timezone-aware increasing periods, non-negative totals and hashed receipts, then sums known device totals,
retains every warning and sets cross_device_provable: false. Aggregate totals
are not evidence of subscription, credit or account savings. Report only
bytes/tokens recorded in the supplied artifacts; unavailable actual usage must
remain unavailable rather than an estimate.
See usage report behavior, measurement rules and the result contract.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.