tokens
Skill2 starsChanged 4 months agoMITView on GitHub
Daily/cache/module token + USD breakdown. Wraps team.sh tokens — the meter the daemon enforces.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- Luclegay/claude-memory-kittheir own version, first seen Nov 16, 2026
- aibtcdev/skillstheir own version, first seen Nov 10, 2026
- sukirman1901/frontend-experttheir own version, first seen Sep 10, 2026
- dkadts/landing-kit-buildingtheir own version, first seen Aug 19, 2026
- educlopez/ui-crafttheir own version, first seen Aug 17, 2026
- nitekeeper/ateliertheir own version, first seen Jun 26, 2026
Used with
Projects with it also use polish and audit.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
HK-hubSkillpolish
Performs a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping. Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great.
Also in 3 projects that use this
OpenAISkillaudit
Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.
Also in 3 projects that use this
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- educlopez/ui-craft★ 441same name
- aibtcdev/skills★ 11same name
- sukirman1901/frontend-expert★ 9same name
- dkadts/landing-kit-building★ 2same name
- PeterCang/claude-tokens-plugin★ 1same name
- 15yotsuka/claude-skills★ 0same name
- Luclegay/claude-memory-kit★ 0same name
- nitekeeper/atelier★ 0same 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.
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Read-only wrapper around team.sh tokens.
“Common” is measured: kept by at least 6 in 10 of the 5 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
/tokens — Token + USD usage
Read-only wrapper around team.sh tokens. Reports the same numbers the
daemon uses to enforce hourly and daily cost caps.
Usage
/tokens # module/role/model breakdown (all modules)
/tokens --daily # last 14 days: input/output/cache + USD total
/tokens --cache # cache hit ratio breakdown
/tokens --wave # group by meta.json.wave
/tokens --json # machine-readable full aggregationteam.sh tokens has no --module <name> filter — the default (no-flag)
report already includes a per-module table; pipe --json through jq to
filter to one module.
What it shows
- Daily breakdown — input, output, cache_creation, cache_read tokens
plus the derived
token_billable_used = input + output + cache_creationused for budget enforcement.cache_readis reported separately at 10% pricing. - Cache hit ratio —
cache_read / (input + cache_read)(matchesteam.sh's--cachecalculation). A healthy pipeline lands above 70% on the analyst/architect/developer hop chain. - Per-module aggregate — same fields scoped to one module's tasks.
- Hourly cap status (round 4) — current hour's spend versus
LSD_HOURLY_USD_HARD_CAP; if the cap is hit the daemon writesteam.pauseduntil the hour rolls.
Output format
=== Tokens — 2026-05-09 ===
input 142,318
output 39,204
cache_creation 18,442
cache_read 286,113
billable 199,964 ($1.42)
cache_hit_ratio 93.9%
hourly_cap $0.21 / $5.00 (LSD_HOURLY_USD_HARD_CAP)Hourly cap reference
LSD_HOURLY_USD_HARD_CAP = 0 # 0 disables; otherwise pause when hour spend exceeds
LSD_DAILY_USD_SOFT_CAP = 0 # info-level Slack notification only
LSD_DAILY_USD_HARD_CAP = 0 # daemon pauses until manual resumeNotes
This is the meter the daemon enforces — /tokens shows the same numbers
the budget guards see. If a daily soft cap fires, /tokens --daily is
the first place to look to confirm the breach.
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.

