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/applynpx skills add melodic-software/claude-code-plugins --skill applygit 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/apply)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/apply"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/apply.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 | $0.00109 | $0.00929 |
| Opus 5 | $0.00055 | $0.00464 |
| Sonnet 5 | $0.00022 | $0.00186 |
| Haiku 4.5 | $0.00011 | $0.00093 |
Grade A, and why
apply 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 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.
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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Consume the machine-readable action-plan JSON emitted by /repo-fleet-hygiene:audit and drive
cleanup for N repositories behind one confirmation gate. This is the executing verb for the
fleet cleanup contract (#2597 / #2609). It is a separate skill from :audit on purpose: the audit's
allowed-tools grant matches any argv on audit-fleet.sh, so an execute flag there would widen
mutation authority silently.
Default is dry-run (evidence refresh + ordered preview, no mutation). Execution requires an
explicit --apply, then interactive confirmation or --yes for non-interactive consent.
Non-negotiable boundary
- Never run without
--plan-filepointing at a prior audit plan (schema_version: 1). - Never treat plan tips as authorization. Re-derive every mutable OID immediately before delete.
- Skip fail-closed on OID drift, missing plan OID, protected/current/worktree-attached branches, locked or stranded worktrees, or unknown operations.
- Own batched
merged-local-branchdeletion here (repo-hygiene branch deletion stays interactive / per-repo and is not batched). - Order:
delete-merged-local-branchesbeforecleanup-worktrees.
Arguments
Parse $ARGUMENTS and pass them through to the bundled script. Supported flags:
--plan-file <path>(required): action-plan JSON from a prior audit (--plan-fileon audit, or the temp path named in the audit report).--apply: opt into mutation after the batch confirmation gate.--yes/-y: skip the interactive prompt (required for non-interactive--apply).
Reject any other flag. Run exactly once:
${CLAUDE_SKILL_DIR}/scripts/apply-plan.sh <validated-and-quoted-arguments>
Confirmation gate
| Session | Flags | Behavior |
|---|---|---|
| Any | (default / no --apply) |
Dry-run preview only |
| Interactive tty | --apply |
Prompt once for the whole plan; decline → mutate nothing |
| Interactive tty | --apply --yes |
Apply without prompt |
| Non-interactive | --apply without --yes |
Print plan, stop (exit 3), mutate nothing |
| Non-interactive | --apply --yes |
Apply |
What ships with it
3 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.
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 · 76 lines · 109 tokens per session scan A 06616d35ce1e
apply is a skill published in the GitHub repository melodic-software/claude-code-plugins (15 stars, last pushed today), licensed MIT. It adds 109 tokens to every session and 929 once invoked, about $0.0005 per session on Opus 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
parallel-orchestrator
Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…
parallel-worker
Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree, assigned scope, commit prefix, parallel task.
review-and-fix
Run /review on the current branch, save findings as a tracker file, ask the user which items to fix, then fix and commit each selected item in an isolated sub-agent (one commit per item). Use when the user says "review and fix", "review then apply", "fix review issues", or any variation meaning "run review then walk…
ship-changes
Audit uncommitted changes for missing documentation updates, then commit, push, and open a pull request. Use when the user says "ship this", "commit and push", "open a PR", or any variation that means "wrap up the current working state into a published PR.".
core-workflow
Detailed development workflow patterns, checklists, and standards. Auto-loads for complex tasks, planning, debugging, testing, or when explicit patterns are needed. Contains session protocols, git conventions, security checklists, testing strategy, and communication standards.
setup-pre-commit
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests. Use when user asks to "add pre-commit hooks", "setup husky", "setup pre-commit", "configure lint-staged", or wants commit-time formatting/typechecking/testing. Don't use for running linters manually or writing tests.