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/runpod/flash/flash-explorernpx skills add runpod/flash --skill flash-explorergit clone --depth 1 https://github.com/runpod/flashWhat 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 | $0.00000 | $0.01032 |
| Opus 5 | $0.00000 | $0.00516 |
| Sonnet 5 | $0.00000 | $0.00206 |
| Haiku 4.5 | $0.00000 | $0.00103 |
Grade A, and why
flash-explorer 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flash Framework Explorer Skill
When to Use
Use this skill when:
- Exploring the runpod-flash framework codebase
- Understanding class hierarchies and relationships
- Finding where methods or classes are defined
- Checking what decorators are used in the codebase
- Getting a quick overview of file structure
Workflow
Step 1: Query the Code Intelligence Database FIRST
Before reading any files, use the MCP code intelligence tools:
Finding a symbol:
- Use
find_symboltool with the symbol name
Understanding a class:
- Use
get_class_interfacetool with the class name
Exploring a file:
- Use
list_file_symbolstool with the file path
Finding decorated functions:
- Use
find_by_decoratortool (e.g., decorator="remote")
Listing all classes:
- Use
list_classestool
Step 1.5: NEVER Use Bash Commands for MCP Tool Tasks
PROHIBITED patterns - use MCP tools instead:
❌ DO NOT use tail, grep, or cat for test output analysis
✅ DO use parse_test_output MCP tool after running tests
❌ DO NOT use grep or find to search for symbols/classes/methods
✅ DO use find_symbol, list_classes, or find_by_decorator MCP tools
❌ DO NOT use Read tool to scan files for class definitions or interfaces
✅ DO use get_class_interface or list_file_symbols MCP tools
Step 2: Only Read Full Files When Necessary
After querying the code intelligence database, only use the Read tool if:
- You need to understand the implementation details
- The database doesn't have the specific information you need
- You need to see the full context around a symbol
Analyzing Test Results
After running tests (make test-unit, make test, pytest), ALWAYS use parse_test_output MCP tool to analyze results:
Good - Use MCP tool (~200 tokens):
- Run:
make test-unit - Pass output to
parse_test_outputMCP tool - Get structured failures, coverage, passed tests, summary
- No manual parsing needed
Bad - Using bash commands (~20,000+ tokens):
- Run:
make test-unit > output.txt - Use
tail,cat, orgrepon output file - Manually parse failures and coverage
- Excessive token usage, poor context extraction
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 · 118 lines · 0 tokens per session scan A 0383d67ad397
flash-explorer is a skill published in the GitHub repository runpod/flash (182 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,032 tokens. 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
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…