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/fragcap/plugin/searchnpx skills add fragcap/plugin --skill searchgit clone --depth 1 https://github.com/fragcap/pluginWhat 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 | $0.00034 | $0.00603 |
| Opus 5 | $0.00017 | $0.00302 |
| Sonnet 5 | $0.00007 | $0.00121 |
| Haiku 4.5 | $0.00003 | $0.00060 |
Grade A, and why
search scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Search Capsules
Search across all FragCap users for capsules relevant to the user's current problem. Uses the GitHub Pages registry (no rate limit, no auth required).
Script Convention
FRAGCAP_DATA="${CLAUDE_PLUGIN_DATA}" node "${CLAUDE_PLUGIN_ROOT}/scripts/<n>.mjs" [args]
If a script exits with a non-zero code or returns { error: "..." }, stop immediately and surface the error to the user. Never silently retry with a different command or skip the step.
When to Activate
- User runs
/fragcap:search <query> - User asks "has anyone solved this before" or similar
Flow
-
Get query:
- If
$ARGUMENTSis provided, use it as the search query. - Otherwise, ask: "What problem are you working on?"
- If
-
Search — run
search.mjs <query>. It returns{ results: [...], total_found, keywords }. -
Display results — show a compact numbered list with status, problem, tags, and author.
- If no results: "No matching capsules found. Try broader keywords or different terms."
- If
total_found> 5: mention there are more results.
-
Detail on demand — present options inline matching the numbered list above, do not ask the user to type a gist ID:
[1] View details [2] View details ... [0] DoneFor each selected result, run
fetch-capsule.mjs <gist-id>and present the full capsule content (problem, attempts, pitfalls, solution, snippet). The response also includesraw_skill— the full SKILL.md content. -
Install option — after viewing details, offer:
[1] Install as local skill [2] Back to resultsIf the user picks install, run
install-capsule.mjs <gist-id>. This writes the SKILL.md to.claude/skills/in the current project, making it automatically available in future sessions. -
Apply — if a capsule is relevant, suggest how it might apply to the user's current work.
Error Handling
- If
search.mjsfails: show the error message and stop. - If
fetch-capsule.mjsfails on a selected result: show the error and offer to try another result.
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 · 58 lines · 34 tokens per session scan A 4f1294b901dc
search is a skill published in the GitHub repository fragcap/plugin (2 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 603 once invoked, about $0.0002 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…