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/echoomegaprime/echo-qcoder/qcoder-vision-operatornpx skills add echoomegaprime/echo-qcoder --skill qcoder-vision-operatorgit clone --depth 1 https://github.com/echoomegaprime/echo-qcoderWhat 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 | $0.00062 | $0.00450 |
| Opus 5 | $0.00031 | $0.00225 |
| Sonnet 5 | $0.00012 | $0.00090 |
| Haiku 4.5 | $0.00006 | $0.00045 |
Grade A, and why
qcoder-vision-operator 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.
What it actually says
QCoder Vision Operator
Expected input
Require a specific visual question and an authorized artifact, page, tab, device, or camera source. Prefer the smallest source that can answer it.
Required sequence
- For a local image, preserve the original and use an available image/OCR capability that returns bounded structured evidence.
- For web UI, reserve a dedicated ShadowGlass tab, navigate through scoped
claude.shadowglass.*capabilities, and collect the accessibility tree, visible text, console/network evidence, and screenshots needed for the claim. - Never read protected fields or capture secrets. Use the opaque Vault-to-browser transfer workflow when credentials must enter an allowlisted field.
- For a camera or home-device source, use only the current role-scoped ECHO vision or smart-home capability and the requested device. Do not enumerate unrelated people or locations.
- Treat the 27B coding model as text-first. When pixels require semantic vision, route the artifact to a Qwen3-VL or existing ECHO vision sidecar and return structured observations to QCoder.
- Keep the vision sidecar off the two QCoder GPUs while the 27B lease is active unless capacity has been measured and the lease controller explicitly permits co-residency.
Verification
For UI claims, combine at least two applicable evidence types: screenshot, accessibility tree, DOM-visible text, console, network trace, or deterministic UI test. A screenshot alone is not proof of backend behavior.
Stop conditions
Stop if the source is not authorized, the tab cannot be isolated, protected-field readback is active, a visual result would expose restricted personal data, or no compatible vision backend is available. Report the missing capability without inventing an observation.
Output format
Return the source identity, observation time, bounded observations, confidence, corroborating evidence, and any inaccessible region or unresolved ambiguity.
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 · 32 lines · 62 tokens per session scan A ab2b25241feb
qcoder-vision-operator is a skill published in the GitHub repository echoomegaprime/echo-qcoder (0 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 450 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…