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/mduffy37/claudeworks/suggest-pluginsnpx skills add Mduffy37/claudeworks --skill suggest-pluginsgit clone --depth 1 https://github.com/Mduffy37/claudeworksWhat 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 | $0.00073 | $0.04843 |
| Opus 5 | $0.00036 | $0.02422 |
| Sonnet 5 | $0.00015 | $0.00969 |
| Haiku 4.5 | $0.00007 | $0.00484 |
Grade A, and why
suggest-plugins 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 2d 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 — 264 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running an interactive discovery session over the curated ClaudeWorks marketplace and the user's local ~/.claude/{skills,agents,commands}/ plugins. Unlike a one-shot recommender, this skill stays resident across multiple user turns: the user searches, you present, the user refines, you re-search, the user picks, you install + add + exclude, the user searches again, and so on until they say they're done. Treat conversational follow-ups as expected, not as pivots.
The skill can perform three kinds of mutation on the user's profile, each gated by an explicit confirmation turn:
- Install a not-yet-installed plugin from its
sourceUrlviainstall-plugins.js. - Add an (already-installed or just-installed) plugin to the active profile via
patch-profile.js add-plugins. - Exclude items on a mega-bundle plugin via
patch-profile.js set-excluded, so only the items that matched the user's query are enabled.
Retrieval mechanics are shared with create-profile via retrieve-plugins.js. You do not grep or jq the marketplace yourself.
Session state (maintained across user turns)
Track these mentally across the entire session. Re-anchor every turn by printing a one-line header at the top of each response:
[suggest-plugins | <profile> | added: <N> | shown: <M>]
targetProfile— the profile you are editing. Locked on Step 0; does not change mid-session. If the user says "actually editfrontend-devinstead", end the current session with a summary, then ask them to re-invoke/suggest-pluginsfrom a session running underfrontend-dev(or pickfrontend-devexplicitly on a fresh invocation).shownPicks— every pick you have presented, numbered continuously across turns. When the user says "add #7" on turn 4,#7is the 7th pick you've shown overall, not the 7th pick from the most recent search.addedThisSession— picks that have been written toprofiles.jsonduring this session. Used for the closing summary and to avoid re-offering picks the user already added.
The anchor line is not cosmetic — it is a state-persistence hack. Claude's context compresses as conversations grow, and the skill body (loaded once at invocation) is the first thing that becomes stale memory. Re-printing the anchor every turn keeps the essential state in the most-recent messages, which are the ones least likely to be compacted.
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.
- 2d ago First seen · 264 lines · 73 tokens per session scan A b446807a2022
suggest-plugins is a skill published in the GitHub repository Mduffy37/claudeworks (11 stars, last pushed 3mo ago), licensed MIT. It adds 73 tokens to every session and 4,843 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
brainstorming
Use this BEFORE any creative or feature work: building a new feature, adding functionality, changing behavior, or making a nontrivial design decision. Turns the user's request into a validated design — recorded as a spec-graph task-spec — before any implementation. Do not skip this because a change looks small.
shipping-a-pr
Use when finished work needs to ship as a pull request, or when the ask is about a PR — creating one, bringing it up to date, adding screenshots, watching its checks, or addressing its review comments. Not for reviewing a PR you are not shipping.
writing-specs
Use when a workflow step drafts or revises a spec artifact — a goal-and-requirements, an architecture, or a module SPEC — or when a workflow skill names it at such a step. The shared quality bar for specs — not a workflow, nothing to execute.
clarify
Adaptive requirements clarification with auto-depth routing. Shallow (Q&A) for simple tasks, Deep (exploration + DRAFT + PLAN) for complex ones. Escalates automatically when ambiguity persists.