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 RockyHong/super-bootstrap --skill resolve-pluginsgit clone --depth 1 https://github.com/RockyHong/super-bootstrapWrote 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/rockyhong/super-bootstrap/resolve-plugins)<a href="https://agentmods.dev/skills/rockyhong/super-bootstrap/resolve-plugins"><img src="https://agentmods.dev/badge/skills/rockyhong/super-bootstrap/resolve-plugins/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/rockyhong/super-bootstrap/resolve-plugins"><img src="https://agentmods.dev/badge/skills/rockyhong/super-bootstrap/resolve-plugins.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00135 | $0.05038 |
| Opus 5.5 | $0.00054 | $0.02015 |
| Sonnet 5.5 | $0.00027 | $0.01008 |
| Haiku 4.5 | $0.00014 | $0.00504 |
Grade A, and why
resolve-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 17d 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resolve Plugins — Curate & Pin
Curate Claude Code skill / MCP / hook picks against live upstream sources and write them to .claude/settings.json. Designed for two callers: standalone refresh (/super-bootstrap:resolve-plugins) and gated tier-2 curation (run by /super-bootstrap:setup once seed docs are substantive).
When to Use
Caller: standalone refresh (/super-bootstrap:resolve-plugins) or gated tier-2 curation (run by /super-bootstrap:setup once seed docs are substantive). Same execution path.
Phase 1: Read inputs (or fail loud)
Read inputs from files: docs/techstack.md, docs/overview.md, .claude/settings.json — caller passes no state.
Required input
docs/techstack.md — drives stack-matched picks. Read § Runtime, § Framework, § Key Dependencies.
If missing → fail loud:
No
docs/techstack.mdfound./super-bootstrap:resolve-pluginsreads stack signal from harness-seeded docs. Run/super-bootstrap:harness-bootstrapfirst to seed the harness, then re-run/super-bootstrap:resolve-pluginsif you want a standalone refresh.
Don't silently scan manifests — manifest detection is harness's job. Doing it here would duplicate logic.
Workflow-tools signal (priority order)
- Existing
.claude/settings.jsonpinned MCPs — Notion MCP pinned → docs-heavy workflow. Linear MCP pinned → ticket-driven. Slack MCP pinned → team comm. Etc. Strong signal — user already explicitly enabled the tool. <!-- harness-meta -->block indocs/overview.md— structuredexternal-tools:record (seeded[github]by the runway, updated manually or via the entry skill). Parse the YAMLexternal-tools:list. Strong signal — committed in the docs, not inferred. Robust to prose drift.- Keyword scan of
docs/overview.mdprose — phrases like "Notion docs", "Linear tickets", "Slack standup". Weak signal, brittle, but cheap. Fallback only when (1) and (2) absent (e.g. legacy harness-bootstrapped repos predating the meta block). - Prompt user once with the external-tools MCQ below if none of (1)–(3) yields signal:
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.
- 17d ago Changed · +1 lines eb9fea8d2541
- 24d ago Changed · +2 tokens per session 9c53cfed013e
- 1mo ago First seen · 269 lines · 133 tokens per session scan A 62c6aac393d8
resolve-plugins is a skill published in the GitHub repository RockyHong/super-bootstrap (3 stars, last pushed 8d ago), licensed MIT. It adds 135 tokens to every session and 5,038 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
c
OpenPaw coordinator — routes requests to skills, manages memory, knows what's installed. Use /c for any task.
janitor-discover
Find new skills on GitHub or check a specific skill before installing. Use when the user wants to search for skills, evaluate a skill URL, check overlap and security risk before installing, or compare a local skill against alternatives. Trigger with '/janitor-discover'.
janitor-value
Show whether each skill is earning its context-window cost — combined tokens-used view sorted by waste. Use when the user asks 'are my skills worth it', 'what's my context budget', 'which skills are dead weight', or wants to audit skill value, token cost, or usage. Trigger with '/janitor-value'.
skill-authoring
Creates and structures SKILL.md files for AI coding agents, including YAML frontmatter, trigger phrases, directive instructions, decision trees, code examples, and verification checklists. Use when the user asks to write a new skill, create a skill file, author agent capabilities, generate skill documentation, or…
github-pr-review
Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, verify PR readiness, review PR comments, analyze review feedback, evaluate PR comments, assess review suggestions, or…
find-skills
Discovers, searches, and installs skills from multiple AI agent skill marketplaces (400K+ skills) using the SkillKit CLI. Supports browsing official partner collections (Anthropic, Vercel, Supabase, Stripe, and more) and community repositories, searching by domain or technology, and installing specific skills from…