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/refactornator/nanoflash/capabilitiesnpx skills add refactornator/nanoflash --skill capabilitiesgit clone --depth 1 https://github.com/refactornator/nanoflashWhat 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 | $0.00042 | $0.00669 |
| Opus 5 | $0.00021 | $0.00334 |
| Sonnet 5 | $0.00008 | $0.00134 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
capabilities 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/capabilities — System Capabilities Report
Generate a structured read-only report of what this NanoFlash instance can do.
Main-channel check: Only the main channel has /workspace/project mounted. Run:
test -d /workspace/project && echo "MAIN" || echo "NOT_MAIN"
If NOT_MAIN, respond with:
This command is available in your main chat only. Send
/capabilitiesthere to see what I can do.
Then stop — do not generate the report.
How to gather the information
Run these commands and compile the results into the report format below.
1. Built-in Gemini agent tools
NanoFlash always has these tools available (implemented as Gemini function declarations):
bash— run shell commands in your sandbox (timeout 120s)read_file— read files from the workspacewrite_file— write files to the workspacelist_directory— list directory contentssend_message— send a message to the user immediately while still workingweb_fetch— fetch a URL and return the content (timeout 30s, 50KB cap)schedule_task— schedule a recurring or one-time task
2. Optional container tools (bash executables)
Check what optional tools are installed:
which agent-browser 2>/dev/null && echo "agent-browser: available" || echo "agent-browser: not found"
3. Model info
echo "Primary model: ${GEMINI_PRIMARY_MODEL:-gemini-2.5-pro-latest}"
echo "Fast model: ${GEMINI_FAST_MODEL:-gemini-2.0-flash}"
4. Group info
test -f /workspace/group/CLAUDE.md && echo "Group memory: yes" || echo "Group memory: no"
test -d /workspace/extra && echo "Extra mounts: $(ls /workspace/extra/ 2>/dev/null | wc -l | tr -d ' ')" || echo "Extra mounts: none"
Report format
Present the report as a clean, readable message. Example:
📋 *NanoFlash Capabilities*
*Agent:* Gemini (gemini-2.5-pro-latest)
*Built-in Tools:*
• bash — run shell commands in sandbox
• read_file / write_file / list_directory — file I/O
• send_message — send progress updates
• web_fetch — fetch URLs (50KB cap)
• schedule_task — schedule recurring or one-time tasks
*Optional Tools:*
• agent-browser: ✓ (or ✗)
*System:*
• Group memory: yes/no
• Extra mounts: N directories
• Main channel: yes/no
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 · 86 lines · 42 tokens per session scan A 80df29f45563
capabilities is a skill published in the GitHub repository refactornator/nanoflash (5 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 669 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…