Claude Code Skills Marketplace is a collection and marketplace of skills, plugins, agents, and instructions that extend Claude Code with specialized development workflows. It is for developers who want to install existing workflows or create, validate, and package their own Claude Code skills.
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 daymade/claude-code-skills --skill github-sensitive-data-cleanupgit clone --depth 1 https://github.com/daymade/claude-code-skillsWrote 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/daymade/claude-code-skills/github-sensitive-data-cleanup)<a href="https://agentmods.dev/skills/daymade/claude-code-skills/github-sensitive-data-cleanup"><img src="https://agentmods.dev/badge/skills/daymade/claude-code-skills/github-sensitive-data-cleanup/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/daymade/claude-code-skills/github-sensitive-data-cleanup"><img src="https://agentmods.dev/badge/skills/daymade/claude-code-skills/github-sensitive-data-cleanup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 20 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 26 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00111 | $0.04723 |
| Opus 5.5 | $0.00044 | $0.01889 |
| Sonnet 5.5 | $0.00022 | $0.00945 |
| Haiku 4.5 | $0.00011 | $0.00472 |
Grade A, and why
github-sensitive-data-cleanup 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Sensitive Data Cleanup
Overview
This skill guides you through safely removing sensitive data from a Git repository's history and pushing the cleaned history to GitHub. It encodes the hard-won lessons from real incidents: scan first, backup before rewriting, verify after rewriting, and never force-push to a public repo without checking its visibility and fork count.
The bundled scripts automate the mechanical parts:
scripts/scan_repo.py— scan the repo for secrets and private context.scripts/rewrite_history.py— create a backup and rewrite history withgit-filter-repo.scripts/verify_cleanup.py— confirm the sensitive content is gone.scripts/safe_push.py— verify repo visibility and push safely.
This skill is conservative by design. If any safety check fails, it stops and asks for human confirmation rather than continuing.
When to Use This Skill
Trigger this skill when the user:
- Says "scan sensitive data", "扫描敏感信息", "看看仓库有没有泄露".
- Wants to "clean git history", "sanitize history", "rewrite history", "remove secrets from history".
- Has accidentally pushed a secret, private domain, internal IP, or PII to a public repository.
- Is about to force-push to a public repository (even without sensitive data).
- Mentions
git filter-repo,BFG,git-filter-branch, or history rewrite.
Prerequisites
Install these tools once per machine:
# git-filter-repo (modern replacement for git-filter-branch)
brew install git-filter-repo
# gitleaks (secret scanner)
brew install gitleaks
# GitHub CLI
brew install gh
The scripts assume git-filter-repo and gitleaks are on PATH. The skill
will check this before running destructive operations.
Safety Rules (Non-Negotiable)
- Scan before you decide. Never rewrite history based on a hunch.
- Create a backup before rewriting. Use
git bundleor a fresh bare clone. - Verify repo visibility with
gh repo viewbefore any push. Do not infer public/private from the URL or directory name. - Never use
--no-verifyto bypass hooks. If the PII Guard hook fails, fix the underlying issue or add an allowlist; do not bypass. - Use one explicit lease bound to the saved remote commit. A rejected
lease stops the push; never fall back to
--forceor refresh the expected commit to bypass concurrent work. - Verify after rewriting. A clean
git logis not enough; re-run the scanner and do an AI semantic review. - Public repos with forks need extra care. Forks and clones may retain old history. Verify the named exposure and ownership before choosing a route; contact owners only within the authorized recipient/message scope.
What ships with it
8 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/evals.json 2.9 KB
- references/ai_semantic_review_prompt.md 3.6 KB
- references/incident-lessons.md 8.6 KB
- references/tooling_notes.md 3.8 KB
- scripts/rewrite_history.py 10 KB runs code
- scripts/safe_push.py 19 KB runs code
- scripts/scan_repo.py 19 KB runs code
- scripts/verify_cleanup.py 7.9 KB runs code
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.
- 12d ago Changed · +37 lines c4380f5e6de4
- 13d ago Changed · +82 lines 8e699f7d13e4
- 24d ago Changed · -2 lines · -4 tokens per session d97d6a80f7a5
- 29d ago Changed · +10 lines afbc4c149ab6
- 1mo ago First seen · 341 lines · 115 tokens per session scan A 87b580a96c5f
github-sensitive-data-cleanup is a skill published in the GitHub repository daymade/claude-code-skills (1,473 stars, last pushed today), licensed MIT. It adds 111 tokens to every session and 4,723 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
git-commit-writer
Trigger when the user asks to write a commit message, generate a commit from staged changes, review a diff before committing, or says "/commit". Reads git diff --staged and produces an opinionated, convention-matching commit message.