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/sdewell/code-quorum/q-researchnpx skills add sdewell/code-quorum --skill q-researchgit clone --depth 1 https://github.com/sdewell/code-quorumWhat 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 | $0.00124 | $0.02501 |
| Opus 5 | $0.00062 | $0.01251 |
| Sonnet 5 | $0.00025 | $0.00500 |
| Haiku 4.5 | $0.00012 | $0.00250 |
Grade A, and why
q-research 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Q-Research — standalone prior-art digest
One synchronous call, no council, no job_id/q_await. This fronts the same
engine the storm modes use for research-first grounding; use it when the
digest itself is the deliverable.
Arguments
$ARGUMENTS is the research topic, optionally with flags:
--source <s>/-s <s>(repeatable) — restrict to a subset ofarxiv,openalex,europepmc-published,europepmc-preprints,context7,github,huggingface. Default: all seven. "Publications/literature only" means-s arxiv -s openalex -s europepmc-published -s europepmc-preprints.--limit <n>— max results per source (default 5, maximum 20). Below 3 the automatic on-topic verdict cannot fire — see Step 3. The cap stays fixed across lanes, so extra lanes broaden coverage without growing the digest.--purpose methods|currency—methodsis the default: OpenAlex balances all-time canonical/relevance candidates with a recent five-year stratum and retains the stratum labels after deduplication.currencyqueries only the recent five-year stratum.--query-lane <query>(repeatable, at most three) — explicit semantic query formulations. If absent, form the lanes in Step 1 and pass them through the tool'squery_lanesparameter. Literature sources search every lane; artifact sources (Context7, GitHub, and Hugging Face) search only the primary lane.--exploratory— cross-domain mode: the user is hunting structural analogies in other fields, so low topic overlap is expected (reported asLOW-OVERLAP, not a retry demand) and the digest adds a### Field mapof which OpenAlex subfields the primary query lane spans.
Strip the flags from the topic text. If the topic (after removing flags) is empty, ask the user what they want researched.
Step 1 — Form the query lanes
Form two or three genuinely different semantic lanes; do not generate them by merely deleting words from one long query:
- Domain plus method or construct.
- Failure mode, validity question, or limitation.
- Standard, guideline, review, or canonical terminology when applicable.
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 · 180 lines · 124 tokens per session scan A dfaea0810673
q-research is a skill published in the GitHub repository sdewell/code-quorum (0 stars, last pushed 2d ago), licensed MIT. It adds 124 tokens to every session and 2,501 once invoked, about $0.0006 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
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…
research-ideation
Quant-focused research ideation pipeline: scope selection (3 stages) → anchor-first literature grounding → single-core idea generation → iterative refinement → ELO tournament ranking (Final = N+R+C−D) → update evo-memory → user selects direction → expand into manuscript-quality proposal. Optimized for incremental…
quant-experiment-runtime
Quant research experiment executor: discover an offline source database under the workdir's code-repo, build a panel, run a Research Artifact's entry point to compute research-object values, and evaluate IC/ICIR/RANKIC/coverage metrics. Runtime = Experiment Executor; it runs a Research Artifact via a Python-native…
jupyter-live-kernel
Use a live Jupyter kernel for stateful, iterative Python execution via hamelnb. Load this skill when the task involves exploration, iteration, or inspecting intermediate results — data science, ML experimentation, API exploration, or building up complex code step-by-step. Uses terminal to run CLI commands against a…
experiment-pipeline
Guides structured 4-stage experiment execution with attempt budgets and gate conditions: Stage 1 initial implementation (reproduce baseline), Stage 2 hyperparameter tuning, Stage 3 proposed method validation, Stage 4 ablation study. Integrates with evo-memory (load prior strategies, trigger IVE/ESE) and…
manim-explainer
Build reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs, then hand off to the wider video stack if needed. Use when the user wants a clean animated explainer rather than a generic talking-head script.