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/hkuds/openspace/fallback-file-opsnpx skills add HKUDS/OpenSpace --skill fallback-file-opsgit clone --depth 1 https://github.com/HKUDS/OpenSpaceWhat 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 | $0.00022 | $0.00653 |
| Opus 5 | $0.00011 | $0.00327 |
| Sonnet 5 | $0.00004 | $0.00131 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
fallback-file-ops 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 3d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fallback File Operations
Purpose
When execute_code_sandbox or shell_agent fail with 'unknown error' on filesystem operations, fall back to run_shell with explicit mkdir and file write commands. This hybrid approach is more reliable for creating complex project structures.
When to Apply
execute_code_sandboxreturns 'unknown error' on file/directory creationshell_agentfails to write files or create nested directories- You need to create complex project structures with multiple levels
Procedure
Step 1: Detect Tool Failure
Monitor for these failure patterns:
- Error message contains "unknown error"
- File operations silently fail (file not created)
- Directory creation returns success but directory doesn't exist
Step 2: Switch to run_shell
When failures occur, immediately switch to run_shell for filesystem operations:
# Create directory structure explicitly
run_shell: mkdir -p /path/to/nested/directory
# Write files using shell redirection or echo
run_shell: echo "content" > /path/to/file.txt
# Or use cat with heredoc for multi-line files
run_shell: cat > /path/to/file.txt << 'EOF'
line 1
line 2
EOF
Step 3: Verify Creation
After each operation, verify the file/directory was created:
run_shell: ls -la /path/to/created/item
run_shell: test -f /path/to/file && echo "File exists"
run_shell: test -d /path/to/dir && echo "Directory exists"
Step 4: Continue with Hybrid Approach
- Use
run_shellfor all filesystem operations (mkdir, write, copy, move) - Continue using
execute_code_sandboxorshell_agentfor code execution, compilation, or other non-filesystem tasks - Document which tool handles which operation for clarity
Example: Creating Project Structure
# Failed attempt with execute_code_sandbox
execute_code_sandbox: create directory src/components
# Fallback with run_shell
run_shell: mkdir -p src/components
run_shell: mkdir -p src/utils
run_shell: mkdir -p tests/unit
run_shell: echo "// Component file" > src/components/Button.tsx
run_shell: echo "// Utility file" > src/utils/helpers.ts
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.
- 3d ago First seen · 87 lines · 22 tokens per session scan A fc4409471c8e
fallback-file-ops is a skill published in the GitHub repository HKUDS/OpenSpace (7,486 stars, last pushed 21d ago), licensed MIT. It adds 22 tokens to every session and 653 once invoked, about $0.0001 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
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…