Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add serpro69/claude-toolbox --skill implementgit clone --depth 1 https://github.com/serpro69/claude-toolboxWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/serpro69/claude-toolbox/implement)<a href="https://agentmods.dev/skills/serpro69/claude-toolbox/implement"><img src="https://agentmods.dev/badge/skills/serpro69/claude-toolbox/implement/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/serpro69/claude-toolbox/implement"><img src="https://agentmods.dev/badge/skills/serpro69/claude-toolbox/implement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00081 | $0.01788 |
| Opus 5.5 | $0.00032 | $0.00715 |
| Sonnet 5.5 | $0.00016 | $0.00358 |
| Haiku 4.5 | $0.00008 | $0.00179 |
Grade A, and why
implement scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
29 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- evals/js-ts-standalone-loads-implement-guidance/eval.json 2.8 KB
- evals/js-ts-standalone-loads-implement-guidance/test-files/src/map-values.mjs 111 B runs code
- evals/js-ts-standalone-loads-implement-guidance/test-files/src/retry-count.ts 92 B runs code
- evals/no-profile-detection-still-runs/eval.json 2.3 KB
- evals/no-profile-detection-still-runs/test-files/docs/feat/wip/team-handbook/design.md 728 B
- evals/no-profile-detection-still-runs/test-files/docs/feat/wip/team-handbook/implementation.md 321 B
- evals/no-profile-detection-still-runs/test-files/docs/feat/wip/team-handbook/tasks.md 319 B
- evals/no-profile-detection-still-runs/test-files/docs/handbook/onboarding.md 374 B
- evals/python-existing-async-loads-guidance/eval.json 1.9 KB
- evals/python-existing-async-loads-guidance/test-files/pyproject.toml 82 B
- evals/python-existing-async-loads-guidance/test-files/worker.py 162 B runs code
- evals/python-new-file-loads-core/eval.json 1.9 KB
- evals/python-new-file-loads-core/test-files/pyproject.toml 80 B
- evals/python-stub-loads-core/eval.json 1.4 KB
- evals/python-stub-loads-core/test-files/api.pyi 38 B
- evals/python-sync-skips-async-guidance/eval.json 1.4 KB
- evals/python-sync-skips-async-guidance/test-files/background.py 50 B runs code
- evals/python-sync-skips-async-guidance/test-files/labels.py 172 B runs code
- evals/standalone-trivial-fix-runs-pre-write-steps/eval.json 2.9 KB
- evals/standalone-trivial-fix-runs-pre-write-steps/test-files/deploy/web-deployment.yaml 520 B
- evals/trivial-task-runs-pre-write-steps/eval.json 2.3 KB
- evals/trivial-task-runs-pre-write-steps/test-files/docs/feat/wip/greeting-skill/design.md 753 B
- evals/trivial-task-runs-pre-write-steps/test-files/docs/feat/wip/greeting-skill/implementation.md 433 B
- evals/trivial-task-runs-pre-write-steps/test-files/docs/feat/wip/greeting-skill/tasks.md 543 B
- evals/trivial-task-runs-pre-write-steps/test-files/skills/greet/SKILL.md 469 B
- plan-mode.md 1.8 KB
- shared-capy-knowledge-protocol.md 37 B
- shared-profile-detection.md 31 B
- standalone-mode.md 1.0 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed ec10005a6707
- 1mo ago Changed · +2 tokens per session d42261e91765
- 1mo ago First seen · 124 lines · 79 tokens per session scan A 22c335ee746c
implement is a skill published in the GitHub repository serpro69/claude-toolbox (151 stars, last pushed yesterday), with no licence file. It adds 81 tokens to every session and 1,788 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
java-code-review
Review Java code for bugs, duplicate code, correctness risks, maintainability improvements, and missing tests. By default review files modified in git; when the user explicitly names files, classes, packages, or a diff, review that scope instead. Generate a detailed review.md report with actionable comments and fixes.
022-root-cause-analysis
Use when a framed problem needs root-cause investigation rather than a symptom-level fix, applying Five Whys, Fishbone (Ishikawa), Current Reality Tree, and constraint identification. This should trigger when an issue's Root Cause Analysis point of view needs evaluation, or when a maintainer directly asks to find the…
126-java-exception-handling
Use when you need to apply Java exception handling best practices — including using specific exception types, managing resources with try-with-resources, securing exception messages, preserving error context via exception chaining, validating inputs early with fail-fast principles, handling thread interruption…
go-errors
Enforces Go error handling — errors as values, wrapping with %w, errors.Is and errors.As over type assertions, sentinel and custom error types, and when panic is acceptable. Use when writing, reviewing, or debugging Go error paths, and when the user mentions err != nil, error wrapping, errors.Is, errors.As, sentinel…
java-boy-scout
Applies the Boy Scout Rule to Java — leave every file a little cleaner than you found it, with small safe improvements made alongside the change you were asked for. Use when fixing, editing, debugging, or extending existing Java code, and when the user says "while you're at it", "any quick wins", "tidy this up"…
py-boy-scout
Use when fixing, editing, changing, debugging, or working with any Python code. Applies the Boy Scout Rule—always leave code cleaner than you found it. Orchestrates other clean code skills as needed. Also trigger on: "while you're at it", "any quick wins", "improve this a bit", "anything else obviously wrong", or when…