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/dash0hq/dash0-agent-plugin/copilot-local-devnpx skills add dash0hq/dash0-agent-plugin --skill copilot-local-devgit clone --depth 1 https://github.com/dash0hq/dash0-agent-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 | $0.00068 | $0.01045 |
| Opus 5 | $0.00034 | $0.00522 |
| Sonnet 5 | $0.00014 | $0.00209 |
| Haiku 4.5 | $0.00007 | $0.00104 |
Grade A, and why
copilot-local-dev 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the Dash0 Copilot plugin locally
The public install path (copilot plugin marketplace add dash0hq/dash0-agent-plugin
copilot plugin install dash0-agent-plugin@dash0) needs the branch pushed and a release carrying thecopilot-on-eventbinary. For local dev we skip both by registering a throwaway local marketplace (the repo's real.github/plugin/marketplace.json, renamed so it can't clash with the productiondash0one) that points at this repo'scopilot/package, installing it the real way, and dropping a locally-built binary where the bootstrap looks (so it skips the download).
This exercises the actual packaging — manifest loading, camelCase hooks.json,
${PLUGIN_ROOT} resolution, the dash0-configure skill, the bare-install guard —
not a hand-wired approximation.
Install / update
Run the setup script (idempotent):
.claude/skills/copilot-local-dev/setup.sh
It stages the marketplace, marketplace add + plugin installs it, and builds
the binary into
~/.copilot/plugin-data/dash0-local/dash0-agent-plugin/bin/.
The install registers the hooks itself, through the manifest's hooks key. If a
session emits no spans, run with --log-level debug --log-dir <dir> and grep the
log for hook: a fired hook logs [hook stderr] dash0: ….
Then, once, set credentials + enable native OTel — start copilot and run:
/dash0-configure
(That writes ~/.copilot/dash0-agent-plugin.local.md and installs a launch
function enabling Copilot's native OTel into
~/.local/state/dash0-agent-plugin/copilot/otel — the source of per-turn
token/cost/model.) Open a fresh shell, then use copilot normally; tool and
chat spans land in your Dash0 dataset.
Iterate
- Changed Go code (
cmd/copilot-on-event,internal/source/copilot): rebuild only —.claude/skills/copilot-local-dev/setup.sh --rebuild— then start a newcopilotsession. - Changed plugin files (
copilot/hooks.json,plugin.json, the skill, the bootstrap): full re-run —.claude/skills/copilot-local-dev/setup.sh— to reinstall.
What ships with it
2 files 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.
- yesterday Changed · +11 lines 1996e487c7e3
- 3d ago First seen · 72 lines · 68 tokens per session scan A 333e572c79a0
copilot-local-dev is a skill published in the GitHub repository dash0hq/dash0-agent-plugin (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 68 tokens to every session and 1,045 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 2026-08-30.
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…