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/ondrasek/cc-plugins/recommendnpx skills add ondrasek/cc-plugins --skill recommendgit clone --depth 1 https://github.com/ondrasek/cc-pluginsWhat 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 | $0.00070 | $0.01896 |
| Opus 5 | $0.00035 | $0.00948 |
| Sonnet 5 | $0.00014 | $0.00379 |
| Haiku 4.5 | $0.00007 | $0.00190 |
Grade A, and why
recommend 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recommend
Analyzes open issues against codebase activity, severity, and external project trends, then recommends the 3 most impactful issues to work on next.
Critical Rules
- Read-only — never create, modify, or close issues
- Read cross-cutting behaviors first:
skills/shared/references/cross-cutting.md - Always show scoring transparency — every recommendation includes the score breakdown
- Diversify categories — top 3 must come from at least 2 categories
- Exclude issues assigned to others — only recommend unassigned issues or issues assigned to the current user
- Cross-reference develop skill — after presenting recommendations, offer to start work via the develop skill
Prerequisites Check
gh auth status
If this fails, tell the user to run gh auth login first.
Workflow
Phase 1: Gather Context
Collect baseline information about the current user and repository.
# Current user
gh api user --jq '.login'
# Repo metadata
gh repo view --json nameWithOwner,description,defaultBranchRef
# Issues already assigned to me
gh issue list --assignee @me --state open --json number,title,labels,updatedAt --limit 50
# Local branches (to detect in-progress work)
git branch --list | head -30
If the user already has 3+ assigned issues, note this and suggest they may want to finish existing work first (but still proceed with recommendations if asked).
Phase 2: Scan Open Issues
Gather the full set of open issues to score.
# All open issues (capped at 100)
gh issue list --state open --json number,title,labels,assignees,createdAt,updatedAt,comments,author --limit 100
# Targeted queries for high-signal subsets
gh issue list --state open --label "bug" --json number,title,labels,updatedAt --limit 30
gh issue list --state open --search "no:label" --json number,title,createdAt --limit 20
gh issue list --state open --search "no:assignee" --json number,title,labels,createdAt --limit 30
If the repo has 0 open issues, tell the user and suggest the create skill.
What ships with it
1 file 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 · 192 lines · 70 tokens per session scan A 774aad71e491
recommend is a skill published in the GitHub repository ondrasek/cc-plugins (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,896 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…