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 agentmods add skills/melodic-software/claude-code-plugins/managenpx skills add melodic-software/claude-code-plugins --skill managegit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWrote 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/melodic-software/claude-code-plugins/manage)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/manage"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/manage.svg" alt="Measured on agentmods" 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 | $0.00225 | $0.03321 |
| Opus 5 | $0.00112 | $0.01661 |
| Sonnet 5 | $0.00045 | $0.00664 |
| Haiku 4.5 | $0.00022 | $0.00332 |
Grade C, and why
manage scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| `~/Tools/Kindle_Key_Finder/` directory | `rm -rf` | Yes | How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Personal-use Kindle DRM removal is a fragile multi-tool workflow with state mutations that, if forgotten, leave the user's machine in an awkward state (silent auto-update, stuck firewall rules, half-installed Calibre plugins). This skill captures the lifecycle as discrete reversible actions and tracks every upstream source that drifts independently (Amazon's Kindle for PC release cadence, Satsuoni's DeDRM_tools fork, Kindle_Key_Finder zip with rolling date in URL, techy-notes.com tutorial article).
Scope: Windows-only (Kindle for PC + KFXKeyExtractor are Windows binaries). Single-user. Books the user owns.
Pre-computed context
Probe current state on every invocation. Run scripts/status.sh and read the JSON output before deciding which action applies.
bash "${CLAUDE_PLUGIN_ROOT}/skills/manage/scripts/status.sh"
Output reports: Kindle for PC version, firewall rule presence, ICACLS deny presence, ~/Tools/Kindle_Key_Finder presence, ~/Downloads installer presence, Calibre install presence, Calibre plugin presence (best-effort), book count in My Kindle Content + Calibre Library.
Action router
| Action | When | What it does |
|---|---|---|
| (empty) | Default. Auto-detect from status | If pristine → recommend /kindle-dedrm:setup. If state OK + user mentioned new books → recommend sync. Otherwise emit status report |
setup |
First-time install | Delegates to the dedicated /kindle-dedrm:setup skill (uniform check/apply contract): provisioning walkthrough: download, install Kindle for PC 2.8.0, sign-in checkpoint, sync books, install Calibre plugins, run keyfinder, apply firewall + ICACLS lockdown |
sync |
New books purchased after initial setup | Disable firewall, prompt user to sync in Kindle, delete cached installer, re-enable firewall, re-run keyfinder |
update |
Periodic drift check | WebFetch tutorial URLs + gh API for upstream releases, diff against captured baselines in reference/sources.md, emit drift report. No mutations |
cleanup |
Decommission | Walk through every reversible mutation with per-item Y/N. Default (confirm-each) offers the firewall rule, ICACLS deny, keyfinder, and downloads; --soft limits to tools + downloads (keeps the firewall/ICACLS lock and Kindle for PC); --full also offers to uninstall Kindle for PC and remove Calibre plugins. The Calibre Library is never offered |
status |
Diagnostic | Same as default empty action |
What ships with it
15 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 4.4 KB
- reference/sources.md 7.1 KB
- reference/troubleshooting.md 9.2 KB
- reference/versions.md 8.4 KB
- reference/workflow.md 11 KB
- scripts/check-drift.sh 6.9 KB runs code
- scripts/check-drift.test.sh 3.4 KB runs code
- scripts/cleanup.sh 6.3 KB runs code
- scripts/firewall.ps1 4.6 KB runs code
- scripts/lock-updates.sh 2.8 KB runs code
- scripts/status.sh 4.4 KB runs code
- scripts/sync-finalize.sh 4.0 KB runs code
- scripts/sync-prep.sh 2.1 KB runs code
- scripts/sync-prep.test.sh 13 KB runs code
- tests/firewall.Tests.ps1 9.6 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.
- yesterday First seen · 174 lines · 225 tokens per session scan C 9ef5d690e605
manage is a skill published in the GitHub repository melodic-software/claude-code-plugins (15 stars, last pushed today), licensed MIT. It adds 225 tokens to every session and 3,321 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
factsheet-design
Print design system for systemprompt.io PDF factsheets and one-pagers. Light branded containers (never dark glassmorphism), print token table, sp-card asymmetric corners in points, full-width SVG diagram rules, WeasyPrint constraints, and the two-page budget discipline. Load before creating or editing any factsheet…
brief-compliance-check
Check a LaTeX coursework submission against the requirements in a supplied PDF assessment brief. Use when verifying format, required sections, word limits, or deliverables before submission. Not for general prose proofreading; use $proofread.
document-skills
Professional document creation, editing, and analysis for Office formats (docx, pdf, pptx, xlsx). Use when working with Word documents, PDFs, PowerPoint presentations, or Excel spreadsheets.
wiki-ingest
Digest a course source file into the wiki. This skill should be used when the user says "ingest", "消化", "process this PDF/slide", or drops a course file into raw/ and wants it turned into wiki pages. Reads the source, deduplicates via manifest, creates source + concept pages, and finds cross-course connections.
solve-constraint-puzzle
For constraint satisfaction: Sudoku, scheduling, N-queens, logic puzzles, SAT-like problems, assignment problems. Uses propagate-then-search pattern.
count-combinations
For probability and counting: permutations, combinations, sample spaces, Monte Carlo simulation, brute-force enumeration, card/dice problems.