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-helpnpx skills add sdewell/code-quorum --skill q-helpgit 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 | $0.00071 | $0.00800 |
| Opus 5 | $0.00036 | $0.00400 |
| Sonnet 5 | $0.00014 | $0.00160 |
| Haiku 4.5 | $0.00007 | $0.00080 |
Grade A, and why
q-help 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions
Print everything below the ---OUTPUT--- line verbatim as your response. Do not paraphrase, summarize, omit sections, or add commentary before or after. Stop after the last line. This skill is a static cheat sheet — your job is to surface it to the user, not to interpret it.
---OUTPUT---
code-quorum — quick reference
code-quorum v0.0.69
Modes
| Workflow | When |
|---|---|
q-plan <task> |
Second-opinion plans before committing. Convergence. |
q-brainstorm <topic> |
Wide spread of testable ideas, grounded in prior art by default (research-first; --no-research opts out). Preserve divergence. |
q-skystorm <topic> |
Forward-research blue-sky. Map the cross-domain topology in the literature → dream → ground → synthesize. |
q-validate <plan-path> |
Critical pushback on a draft plan. 2-round default; --extended = 4 rounds with stance rotation at R3. |
q-review [target] |
Critical pushback on real code changes (branch/PR/range/whole codebase). Convergence into a findings table. --scope <path> bounds it; 2-round default, --extended = 4. |
q-research <topic> |
Standalone prior-art digest with semantic query lanes, per-source/lane status, OpenAlex methods/currency purpose, and separate published/preprint Europe PMC sources. No council — one call. -s <source> restricts; --exploratory hunts cross-domain analogies. |
Invocation
The host can select a workflow from a matching plain-language request. To select one explicitly:
| Surface | Example |
|---|---|
| Claude Code | /q-plan <task> |
| Codex | $code-quorum:q-plan <task> |
| Shell | uv run quorum q-plan <task> |
Use the same q-* workflow name in Claude Code and Codex. q-skystorm and q-help are host-only skills; they have no shell command. The standalone shell command is uv run quorum research <topic>; --exploratory is host-only, and the shell research command is the grounded digest.
Default council
The host never runs as a subprocess seat.
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 · 59 lines · 71 tokens per session scan A ae8587098b22
q-help is a skill published in the GitHub repository sdewell/code-quorum (0 stars, last pushed 2d ago), licensed MIT. It adds 71 tokens to every session and 800 once invoked, about $0.0004 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
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
hedging-strategy
Hedging strategy design (beta hedge / option protection / tail risk / cross-asset hedging), including hedge-ratio calculation and cost evaluation.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
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…
oma-hwp
Convert HWP / HWPX / HWPML files to Markdown using kordoc. Extracts text, headings, tables, lists, images, footnotes, and hyperlinks. Use for Korean word processor files (Hangul), government documents, and AI-ready data preparation.
error-recovery
Standard recovery patterns for all squad agents. When something fails, adapt — don't just report the failure.