Guides

One page per job, written from the measurements behind every mod page: what a thing costs you per session, what the scan found in it, and which five or six are worth starting with.

  • Backend skills: choosing API and database help without paying for clutter

    We measured 12,025 backend skills. The median preloads 58 tokens, the heaviest 720, before your API task starts. Here is how to choose one.

    10 September 2026 · 12,025 skills · 3,761 repositories · names 10 mods

  • Slash commands: choose the right shape for a named task

    42,815 slash commands measured: compare the 17-token session cost, security scan, originals and copies, then choose the right command for named work.

    10 September 2026 · 42,815 commands · 5,886 repositories · names 10 mods

  • Plugins: what one install brings into your session

    We measured 16,285 Claude Code plugins. Learn what one installation brings, what the scan found, and why its per-session token cost may be unknown.

    10 September 2026 · 16,285 plugins · 9,895 repositories · names 8 mods

  • Settings permissions: know what you are opening

    2,888 settings measured: see what permissions open, what the scan flags, and which project files are worth reading before you install one.

    10 September 2026 · 2,888 settings · 2,888 repositories · names 8 mods

  • Claude Code skills: the preload price before you use one

    Claude Code skills can cost 58 tokens before use. We measured 247,505 skills, scanned their contents, and picked six useful starting points.

    10 September 2026 · 247,505 skills · 30,748 repositories · names 10 mods

  • Subagents: choosing focused workers outside your context

    A practical guide to choosing subagents, the 43-token median, where their instructions live, what the scan found, and when another mod fits better.

    10 September 2026 · 35,824 subagents · 4,962 repositories · names 10 mods

  • Code review skills: what they cost and which ones read the diff

    Code review skills measured: compare the 54-token median, full-session cost, scan grades, findings, originals and the best diff readers.

    10 September 2026 · 13,127 code review skills · 5,297 repositories · names 9 mods

  • Copilot instructions: what your first prompt inherits

    Copilot instructions: 2,056 files measured, with a 683-token median per session, scan findings, originals and practical starting points.

    10 September 2026 · 2,056 copilot-instructions.md files · 2,056 repositories · names 11 mods

  • Data and AI skills: choose one for notebooks and models

    7,868 data and AI skills measured: compare session cost, scan findings, copies and fit for notebook, model and data work before installing.

    10 September 2026 · 7,868 skills · 2,870 repositories · names 10 mods

  • Debugging skills: choose a method without paying for it all day

    Debugging skills can cost 55 tokens every session even when unused. Compare scan grades, risky lines, copies, and five ways to investigate bugs.

    10 September 2026 · 11,549 skills · 5,191 repositories · names 9 mods

  • Design skills: choose the right help for your interface

    11,027 design skills measured: session cost, scan grades, findings, copies, and six starting points for choosing interface help in real work.

    10 September 2026 · 11,027 skills · 4,119 repositories · names 10 mods

  • DevOps skills for deployment, CI and cloud work

    15,154 DevOps skills measured for deployment, CI and cloud work, with costs, scan findings and practical picks for your next release.

    10 September 2026 · 15,154 DevOps skills · 4,221 repositories · names 10 mods

  • Frontend skills: choosing what loads for component work

    We measured 11,514 frontend skills. See what loads every session, what the scan found, and which six are sensible starting points.

    10 September 2026 · 11,514 skills · 3,867 repositories · names 9 mods

  • GEMINI.md: the file Gemini CLI pays for every session

    GEMINI.md costs a median 512 tokens every Gemini CLI session. See what the scan found, which files are heaviest, and five worth studying first.

    10 September 2026 · 759 GEMINI.md files · 759 repositories · names 9 mods

  • Git skills: commits, branches and pull requests worth the cost

    12,055 Git skills measured: the median session load is 51 tokens, the 90th percentile 120, and six are worth a closer look.

    10 September 2026 · 12,055 skills · 5,187 repositories · names 9 mods

  • Originals and copies: find the first skill

    15,698 skills measured: learn to spot the original, read copy counts, compare token preload, and choose where a copied file deserves your trust.

    10 September 2026 · 15,698 skills · 2,580 repositories · names 9 mods

  • Planning skills: choose a plan before code

    26,049 planning skills measured: how to choose a plan before code, what each costs per session, and when a rule or hook fits better.

    10 September 2026 · 26,049 skills · 7,171 repositories · names 9 mods

  • Security skills: who is checking the checker?

    Security skills can inspect your code, but the checker also costs tokens and may ask for access. We measured 15,178 to show the trade-off.

    10 September 2026 · 15,178 skills · 4,229 repositories · names 10 mods

  • Testing skills: choose one that writes tests or runs them

    13,825 testing skills measured: choose a skill that writes or runs tests, see token cost and scan grades, then start with six grounded picks.

    10 September 2026 · 13,825 skills · 5,466 repositories · names 10 mods

  • Skill, command, rule or hook: choose the right mod for the job

    Skill, command, rule or hook? We measured 348,758 mods to show what loads, what runs, what it costs, and when each kind fits.

    10 September 2026 · 348,758 mods · 34,694 repositories · names 7 mods

  • Documentation mods for changelogs and technical writing

    17,683 writing mods measured: costs, scan grades, and practical picks for changelogs, references, and project documentation in coding repositories.

    10 September 2026 · 17,683 mods · 6,909 repositories · names 10 mods

  • What an AGENTS.md file costs you every session

    34,245 instructions files measured. What AGENTS.md, CLAUDE.md and copilot-instructions.md cost on every session, how large projects keep theirs, and what such a file cannot do.

    9 September 2026 · 34,245 instructions files · 26,742 repositories · names 8 mods

  • Claude Code hooks: read the command before you install it

    8,472 Claude Code hooks measured: which event each one fires on, what the scan found in the 27 graded C or D, and six worth reading before you install anything.

    9 September 2026 · 8,472 hooks · 3,816 repositories · names 9 mods

  • Cursor rules: the one setting that decides what they cost you

    We measured 14,110 Cursor rules. Two in three are read into every chat whether you need them or not. Here is what that costs, what the scan found, and five rules worth a look.

    9 September 2026 · 14,110 rules · 3,416 repositories · names 8 mods