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/mend3/vscode-agent-bridge/vscode-workflownpx skills add mend3/vscode-agent-bridge --skill vscode-workflowgit clone --depth 1 https://github.com/mend3/vscode-agent-bridgeWrote 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/mend3/vscode-agent-bridge/vscode-workflow)<a href="https://agentmods.dev/skills/mend3/vscode-agent-bridge/vscode-workflow"><img src="https://agentmods.dev/badge/skills/mend3/vscode-agent-bridge/vscode-workflow.svg" alt="Measured on agentmods" 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 | $0.00063 | $0.00701 |
| Opus 5 | $0.00032 | $0.00351 |
| Sonnet 5 | $0.00013 | $0.00140 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
vscode-workflow 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working through VS Code
A VS Code window is open on this workspace and its editor, language services and diagnostics are available as tools. They answer questions about code structure that text search can only approximate.
Filesystem and terminal tools still work and are still the right choice for many things. The point is not to replace them — it is to stop paying for text-level work when a structural answer exists.
Routing
| Need | Use |
|---|---|
| What the user means by "this", "here", "the file I'm on" | get_active_editor |
| Where is a symbol defined | find_definition |
| Everywhere a symbol is used | find_references (not grep) |
| What breaks if I change this function | get_call_hierarchy |
| What is in this file | get_document_symbols |
| Where does something called X live | find_workspace_symbols |
| Find a literal string, comment, config key | search_workspace |
| Read a file someone may be editing | read_range — live buffer plus its version |
| Rename a symbol | rename_symbol (never a textual replace) |
| Change a specific known range | apply_edit |
| Did my change break anything | get_diagnostics |
| Read a whole file, list files, run git, run tests | your normal tools — the bridge does not duplicate them |
Habits that matter
Acquire context progressively. search_workspace → pick the interesting hits →
read_range on those. Reading whole files to find fifty relevant lines wastes the context
you will need later for the actual work.
Pass version or expect when editing. read_range returns a document version; hand it
back to apply_edit. If the user typed in the file meanwhile, the edit is rejected instead
of silently overwriting their work. Plain file reads come from disk and miss unsaved edits,
so read with read_range when you intend to write.
Rename through the language service. rename_symbol updates references and imports and
leaves comments and unrelated identifiers alone. A workspace-wide text replace cannot tell a
symbol from a substring, and it is the classic way to break a codebase quietly.
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 · 59 lines · 63 tokens per session scan A fd78368aae57
vscode-workflow is a skill published in the GitHub repository mend3/vscode-agent-bridge (0 stars, last pushed 23d ago), licensed MIT. It adds 63 tokens to every session and 701 once invoked, about $0.0003 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…