plugin-cost
/plugin-cost
Report each enabled plugin's per-session token cost and how often it was really used, with cleanup suggestions. Use when asked about plugin/skill token cost, context overhead, or which plugins to disable.
- Author
- rafalfbacc-tech ↗
- Repository
- rafal-tools ↗
- Licence
- MIT
- Last repository change
- 11.11.2026
Assessment and security
- Files in this package
- 2
- Scripts
- 1
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 11.11.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
- 1 scripts in this package. Review them before installing, as Claude may execute them.
Scripts: scripts/plugin-cost.mjs
What it does and when to use it
Report each enabled plugin's per-session token cost and how often it was really used, with cleanup suggestions. Use when asked about plugin/skill token cost, context overhead, or which plugins to disable.
Original author description
Report each enabled plugin's per-session token cost and how often it was really used, with cleanup suggestions. Use when asked about plugin/skill token cost, context overhead, or which plugins to disable.
How it works
SKILL.md has no level-two headings · 18 lines, 228 words
SKILL.md preview
--- name: plugin-cost description: Report each enabled plugin's per-session token cost and how often it was really used, with cleanup suggestions. Use when asked about plugin/skill token cost, context overhead, or which plugins to disable. --- # Plugin Cost 1. Run `node "<this skill's base directory>/scripts/plugin-cost.mjs"`. It takes ~5–10 s. Add `--days N` for another usage window (default 30), `--here` to measure hooks in the current folder (shows folder-specific injections such as a task list; SessionStart hooks then run there for real, UserPromptSubmit hooks still run in an empty folder), or `--no-hooks` to skip running hooks. 2. Show the output unchanged, in a code block. 3. Below it, give at most 3 concrete recommendations in the user's language, based on the Findings and the numbers: - **Never used and costly** → disable globally. - **Used only in a few projects** → disable globally and enable per project. - **Duplicate scopes** → `claude plugin uninstall <id> --scope project --keep-data`, run in that project folder. Never use `disable --scope project` for this: it turns the plugin off there. Include the exact command for each. 4. **Never run `claude plugin disable/enable` or edit settings yourself** unless the user explicitly confirms. Remind them that changes apply from the next session. How the numbers are built: - **Skills** = skill and agent descriptions, from `claude plugin details`. - **Hook** = text that SessionStart hooks inject; the script measures it by running the hooks in an empty temp folder. - **Usage** = counted from local session history in `~/.claude/projects`. - **Token counts** are estimates of about 4 characters per token.
Files in this package (2)
- SKILL.md 2 KB
- scripts/plugin-cost.mjs 12 KB
Versions
The database has no other skills named plugin-cost.
Database snapshot: 13.11.2026 · package version a6019d8ba27e (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100cost-report
Report actual token spend and dollar cost of dispatched work — per agent and total — and flag cost regressions. Use when the user asks "how much did that cost", "token spend", "cost of this run", "cost report", or wants to check for a cost regression after /code-review or an orchestration run. - 100codex-plugin-discovery
Use when a user asks what Codex plugins are available or can be used, wants plugin recommendations for a task, asks to find/search/discover installable plugins, asks about the plugin marketplace, or asks whether a plugin can help with a task. - 100cost-estimate
Estimate the cost of a task before starting it. Analyzes task complexity, predicts token usage, and compares cost across all Claude models. Use when user says 'estimate cost', 'how much will this cost', 'cost estimate', or '/cost-estimate'. - 87profile
Session clock-time AND token/cost analyzer. Reads the foundry plugin's timings.jsonl and invocations.jsonl logs (written by task-log.js) for wall-time, plus Claude Code transcripts (~/.claude/projects/**, main-loop + subagent files) for token usage and USD cost, and merges both… - 100input-token-overheads
Use when context window is filling up too fast or input token cost is too high. Audits overhead sources. - 95dashboard
Open context-guru's dashboard in the browser on the Cleanup page, for deciding what to remove yourself — what carrying each unused capability has really cost since install, with a command builder. Use when the user wants to see the dashboard, look at the data themselves,…