Skip to content
Back to search

skilltally

MarketplaceWorks with Claude CodeGitHub

Real-time skill usage tracking via hooks for Claude Code, Codex, Antigravity & Gemini CLI.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/112516101106--skilltally/badge.svg)](/listings/112516101106--skilltally)

HTML

<a href="/listings/112516101106--skilltally"><img src="/api/listings/112516101106--skilltally/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

# 1. Detect installed agents and register lightweight PostToolUse/AfterTool hooks
npx skilltally install --dry-run
npx skilltally install

# 2. Import historical sessions from local logs
npx skilltally backfill

# 3. Verify hook registration and run live self-test
npx skilltally doctor

# 4. Inspect usage, insights, HTML dashboard, and unused context tax
npx skilltally stats --since 30d
npx skilltally insights --since 30d
npx skilltally dashboard --open
npx skilltally unused --since 90d

Or ask your coding agent directly: *"Which agent skills do I use the most?"*

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 18 lines
  1. {
  2. "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  3. "name": "skilltally",
  4. "description": "Real-time skill usage tracking via hooks for Claude Code, Codex, Antigravity & Gemini CLI.",
  5. "owner": {
  6. "name": "112516101106",
  7. "url": "https://github.com/112516101106"
  8. },
  9. "plugins": [
  10. {
  11. "name": "skilltally",
  12. "description": "Track skill activations and identify unused skills eating context.",
  13. "version": "1.2.1",
  14. "source": "./",
  15. "category": "productivity"
  16. }
  17. ]
  18. }
README.md · README · 158 lines
  1. # skilltally
  2. [![CI](https://github.com/112516101106/skilltally/actions/workflows/ci.yml/badge.svg)](https://github.com/112516101106/skilltally/actions/workflows/ci.yml)
  3. [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
  4. [![Node.js >= 18](https://img.shields.io/badge/node-%3E%3D18-brightgreen.svg)](package.json)
  5. [![Zero Dependencies](https://img.shields.io/badge/dependencies-0-success.svg)](package.json)
  6. Real-time skill usage tracking via hooks for **Antigravity**, **Claude Code**, **Codex**, and **Gemini CLI** — 100% local, zero dependencies.
  7. Find out which agent skills you actually use, and how much context (`KB` / `~tokens/session`) unused skills and plugins cost you on every turn.
  8. ## Quick Start
  9. ```bash
  10. # 1. Detect installed agents and register lightweight PostToolUse/AfterTool hooks
  11. npx skilltally install --dry-run
  12. npx skilltally install
  13. # 2. Import historical sessions from local logs
  14. npx skilltally backfill
  15. # 3. Verify hook registration and run live self-test
  16. npx skilltally doctor
  17. # 4. Inspect usage, insights, HTML dashboard, and unused context tax
  18. npx skilltally stats --since 30d
  19. npx skilltally insights --since 30d
  20. npx skilltally dashboard --open
  21. npx skilltally unused --since 90d
  22. ```
  23. Or ask your coding agent directly: *"Which agent skills do I use the most?"*
  24. ## Supported Agents
  25. | Agent | Real-time hook | History backfill | Plugin / Extension install | Notes |
  26. |---|---|---|---|---|
  27. | **Antigravity** | `PostToolUse` (`read_file\|view_file\|run_command`) | `~/.gemini/antigravity*/brain/` | Native plugin (`plugin.json` + `hooks.json`) | POSIX fast-path forwards `SKILL.md` & `skills/*/(scripts\|bin)/*` (~7 ms skip on misses); preserves `<SKILL>` manual triggers (`via: "slash_command"`); reads `transcript_full.jsonl` when truncated |
  28. | **Claude Code** | `PostToolUse` (`Skill\|Read\|View\|Bash`, `async: true`) | `~/.claude/projects/**/*.jsonl` | `.claude-plugin/plugin.json` | 30 s deduplication window, continuation-read filtering, and `Base directory for this skill:` slash-command backfill |
  29. | **Codex** | `PostToolUse` + `UserPromptSubmit` (`async: true`) | `~/.codex/{sessions,archived_sessions}/` | `.codex-plugin/plugin.json` | Supports `.jsonl.zst` natively on Node `>= 22.15`, `.system`/nested/MCP `skill://`/script detection, forked rollout deduplication, and trust verification via `/hooks` |
  30. | **Gemini CLI** | `AfterTool` (`activate_skill\|read_file\|view_file\|read_many_files\|run_shell_command`) | `~/.gemini/tmp/*/chats/*.{json,jsonl}` | `gemini-extension.json` + `install --host gemini` | `timeout: 5000` ms in `~/.gemini/settings.json`; supports `.json` and `$set.messages` `.jsonl` checkpoints |
  31. ## Plugin & Skill Installation
  32. If you prefer native plugin managers over `npx skilltally install`:
  33. - **Antigravity**: Copy or symlink this repository to `~/.gemini/config/plugins/skilltally` (or run `npx skilltally install --host antigravity`).
  34. - **Claude Code**:
  35. ```text
  36. /plugin marketplace add 112516101106/skilltally
  37. /plugin install skilltally@skilltally
  38. ```
  39. - **Codex**:
  40. ```bash
  41. codex plugin marketplace add https://github.com/112516101106/skilltally.git
  42. codex plugin add skilltally@skilltally
  43. ```
  44. Run `codex`, open `/hooks`, and trust the `skilltally` hooks (`PostToolUse` and `UserPromptSubmit`).
  45. - **Gemini CLI**:
  46. ```bash
  47. gemini extensions install https://github.com/112516101106/skilltally
  48. npx skilltally install --host gemini
  49. ```
  50. - **Companion skill only (`skills.sh`)**:
  51. ```bash
  52. npx skills add 112516101106/skilltally
  53. ```
  54. ## Example Output
  55. ### `skilltally stats --since 30d`
  56. ```text
  57. skilltally — last 30d (2026-10-20 -> 2026-11-19)
  58. hosts: antigravity 35 · codex 12
  59. triggers: auto 38 · manual 9
  60. # skill activations reads last used hosts trend (14d)
  61. 1 requesting-code-review 8 10 2026-11-12 14:03 antigravity, codex ··▁·▃·█··▃·▁··
  62. 2 systematic-debugging 5 9 2026-11-10 09:41 codex ····▁··█··▁···
  63. 3 agent-browser 3 4 2026-11-05 12:18 antigravity, codex ··█···········
  64. installed: 214 · used: 22 · unused: 192 -> run `skilltally unused`
  65. ```
  66. ### `skilltally unused --since 90d`
  67. ```text
  68. Unused enabled skills — last 90d (2026-08-21 -> 2026-11-19): 192 (48.2 KB ≈ ~12,340 tok/session)
  69. context tax: [████████████░░░░] 76% unused (~12,340 / ~16,200 tok/session)
  70. plugin:science 47 skills 14.8 KB ~ 3818 tok/session
  71. alphagenome-atlas-website-links, alphagenome-single-variant-analysis, … (+41)
  72. personal 47 skills 10.6 KB ~ 2729 tok/session
  73. architecture-blueprint-generator, auditing-python-security, … (+41)
  74. Tip: disabling an unused plugin removes all of its skill descriptions from every session context.
  75. ```
  76. ## CLI Reference
  77. | Command | Description | Key flags |
  78. |---|---|---|
  79. | `install` | Install hooks for detected hosts (`runtime/track.mjs` + backups) | `--host all\|antigravity\|claude\|codex\|gemini`, `--dry-run`, `--force`, `--json` |
  80. | `uninstall` | Remove `skilltally` hooks (preserves all other user hooks) | `--host ...`, `--purge`, `--dry-run`, `--json` |
  81. | `doctor` | Check Node version, hook paths, Codex trust, events, and live self-test | `--json` |
  82. | `backfill` | Import historical skill reads/invocations from local logs | `--host ...`, `--since DATE`, `--dry-run`, `--json` |
  83. | `stats` | Usage table sorted by `activations` with 14-day sparklines and trigger ratio | `--since 30d\|all\|YYYY-MM-DD`, `--host`, `--project`, `--by-source`, `--metric reads`, `--json` |
  84. | `top` | Top `N` skills | `-n 20`, plus `stats` flags |
  85. | `unused` | Enabled installed skills with 0 activations and Context Tax breakdown | `--since 90d`, `--host`, `--all`, `--json` |
  86. | `timeline` | ASCII usage bar chart over time | `--skill <name>`, `--by day\|week\|month`, `--since`, `--host`, `--project`, `--json` |
  87. | `chains` | Skill transition chains (`A -> B`), 3-step workflows, and co-occurring pairs | `--since`, `--host`, `--project`, `-n 20`, `--json` |
  88. | `insights` | Runtime tokens & prompt cache hit rate, task durations (`slowestSkills`), heavy `SKILL.md` bodies (`>= 1,500` tokens), opt-in redacted prompt patterns, Context ROI, manual-only triggers, single-project scoping, and model breakdown | `--since`, `--host`, `--project`, `--json` |
  89. | `dashboard` | Generate self-contained offline HTML dashboard (5-metric KPI strip with `Lifetime tokens`, `Peak tokens`, `Longest task`, streaks; SVG Treemap; cache hit rate; workflow chains; Mermaid generator) | `-o <file>`, `--since`, `--host`, `--project`, `--open`, `--json` |
  90. | `prune` | Safely disable 100%-unused plugins or specific unused skills (with backups) | `--since 90d`, `--host all\|antigravity\|codex`, `--plugin <name>`, `--skill <name>`, `--dry-run`, `--json` |
  91. | `export` | Export deduplicated events as JSON or RFC-4180 CSV | `--format json\|csv`, `-o <file>`, `--since`, `--host`, `--project`, `--include-failed` |
  92. | `inventory` | List installed skills, sources, hosts, enabled state, and description sizes | `--no-project`, `--json` |
  93. | `mcp` | Start zero-dependency stdio MCP server (`skilltally_*` tools) | — |
  94. | `debug` | Toggle opt-in raw stdin logging (`on \| off \| status`) | `--json` |
  95. ## Privacy, Performance & Reliability
  96. - **100% local, zero telemetry**: Zero network requests, zero third-party runtime dependencies.
  97. - **No raw arguments or prompts stored**: Only the matched `SKILL.md` path (or `Skill`/`activate_skill` name) and `basename(cwd)` are written to `~/.skilltally/` (`0700` dir, `0600` files). Full `cwd` is omitted unless `store_cwd: true` is set, and redacted prompt previews (`80` chars, secrets/emails/paths stripped) are omitted unless `store_prompts: true` is set in `~/.skilltally/config.json`.
  98. - **Safe by contract**: `track.mjs` never throws, always exits `0`, and always writes `{}` to `stdout` so hooks never interrupt an agent turn.
  99. - **Accurate telemetry & deduplication**: Filters paginated continuation reads, deduplicates repeated same-session triggers within 30 s while preserving manual triggers (`slash_command`/`mention`), deduplicates per-turn token snapshots, merges overlapping turn duration intervals, and computes provider-aware prompt cache hit rates across Anthropic vs. OpenAI/Gemini token schemas.
  100. - **Automatic rotation**: When `events.jsonl` exceeds 20 MB, it rotates automatically to `events-YYYY-MM.jsonl` while reports transparently read all archives.
  101. - **Config backups**: `install` and `uninstall` back up modified host configs to `~/.skilltally/backups/`.
  102. ### Configuration (`~/.skilltally/config.json`)
  103. ```json
  104. {
  105. "exclude_skills": ["skilltally"],
  106. "exclude_sources": [],
  107. "aliases": { "native_swarm": "swarm" },
  108. "store_cwd": false,
  109. "store_prompts": false
  110. }
  111. ```
  112. ## Troubleshooting
  113. - **No events recorded?** Run `npx skilltally doctor` to verify hook paths and run the live pipe self-test.
  114. - **Codex hooks not firing?** Run `codex` and open `/hooks` to review and trust the `skilltally` hooks (`PostToolUse` and `UserPromptSubmit`).
  115. - **Gemini CLI hooks disabled?** Check `"hooksConfig": { "enabled": true }` in `~/.gemini/settings.json`.
  116. - **Inspecting unknown hook payloads:** Temporarily run `npx skilltally debug on`, trigger a skill once, inspect `~/.skilltally/debug.jsonl`, then run `npx skilltally debug off` (which deletes `debug.jsonl` automatically).
  117. ## Development
  118. ```bash
  119. npm test
  120. npm run check:pack
  121. ```
  122. ## License
  123. MIT — [112516101106/skilltally](https://github.com/112516101106/skilltally)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.