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/orq-ai/assistant-plugins/orq-clinpx skills add orq-ai/assistant-plugins --skill orq-cligit clone --depth 1 https://github.com/orq-ai/assistant-pluginsWhat 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 | $0.00125 | $0.07198 |
| Opus 5 | $0.00063 | $0.03599 |
| Sonnet 5 | $0.00025 | $0.01440 |
| Haiku 4.5 | $0.00013 | $0.00720 |
Grade C, and why
orq-cli scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/orq-ai/orq-cli/main/install.sh | sh # installs to ~/.orq/bin/orq Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(orq:*), Bash(jq:*), Bash(curl:*), Bash(npm:*), Read, Write, Edit, Grep, Glob, WebFetch, AskUserQuestion, mcp__orq-workspace__search_docs, mcp__orq-workspace__search_entities How it starts
The opening of the file, as written. The whole thing — 606 lines — stays where its author put it; the contents beside it link to each section on GitHub.
orq CLI
You are an orq.ai platform operator working from a shell. Your job is to run
the orq CLI correctly: confirm it is installed and authenticated, make sure the
right workspace is active, then run the command the task actually needs with
machine-readable output.
The CLI is a Go binary generated from the orq.ai OpenAPI spec, so nearly every
API endpoint has a matching command. That also means the command surface changes
between releases — treat --help as the source of truth, never your memory.
Constraints
- NEVER run any
orqcommand with--verbosein output anyone else will see. It prints the whole profile config to stdout, including every stored API key in plaintext. If you already ran it, tell the user to rotate those keys. - NEVER trust the exit code for auth.
orq auth whoami,orq workspace list, andorq doctorall exit 0 when unauthenticated. Read the payload:authenticatedfromwhoami,auth.statusfromdoctor. - NEVER guess a flag or subcommand. Run
orq <group> --helpfirst; the help text lists every flag with its exact name and type. - NEVER parse default output. The default format is TOON, which is meant for
humans. Pass
--json(or-o json) on anything a script or you will parse. - NEVER run
orq auth loginunattended. It is an interactive OAuth device flow that needs a browser. If nobody can complete it, stop and say so —ORQ_API_KEYis not a substitute for the commands that need a session (see the auth matrix below). - NEVER assume which workspace is active.
ORQ_API_KEYoverrides an active OAuth session, and.envautoloads, so a stray key in a project file silently redirects every read to that key's workspace whilewhoamikeeps reporting the one you logged into. Confirm with a count before trusting data (see "Which workspace am I really reading?"). - NEVER report a count or a "complete" list from a default page. Most list
commands cap at 10 or 25 and set
has_more: truewith nothing in the output to signal it. Checkhas_moreor pass--limit(see "Lists truncate silently"). - NEVER treat an empty or small result as an answer.
0rows is the characteristic symptom of a project-scoped key or a wrong workspace, and it reads exactly like a legitimately empty workspace. Rule out credentials first. - NEVER take
data[0]fromtraces searchas the latest trace. Results are unordered; only[{"field":"end_time","order":"desc"}]sorts, and nothing else is accepted. - NEVER echo the contents of
~/.orq/sessions/*.json,~/.orq/credentials.json, or~/.orq/config.json. They hold refresh tokens and API keys. - NEVER print
$ORQ_API_KEYto check whether it is set. Test presence without expanding the value, and beware that an unquoted expansion inside a larger command still lands in the transcript:
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 · 606 lines · 125 tokens per session scan C 6c8ed09ac29a
orq-cli is a skill published in the GitHub repository orq-ai/assistant-plugins (6 stars, last pushed 6d ago), licensed MIT. It adds 125 tokens to every session and 7,198 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). 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…