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 skills add haru0416-dev/quaere --skill quaere-inventiongit clone --depth 1 https://github.com/haru0416-dev/quaereWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/haru0416-dev/quaere/quaere-invention)<a href="https://agentmods.dev/skills/haru0416-dev/quaere/quaere-invention"><img src="https://agentmods.dev/badge/skills/haru0416-dev/quaere/quaere-invention/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/haru0416-dev/quaere/quaere-invention"><img src="https://agentmods.dev/badge/skills/haru0416-dev/quaere/quaere-invention.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00163 | $0.02373 |
| Opus 5 | $0.00081 | $0.01187 |
| Sonnet 5 | $0.00033 | $0.00475 |
| Haiku 4.5 | $0.00016 | $0.00237 |
Grade A, and why
quaere-invention 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 10d 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.
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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invention Probe
Iron Law
No idea is promoted as novel without naming four things: the default basin it escapes, the assumption it breaks, the mechanism of the break, and the smallest probe that could disconfirm it. An idea that cannot name all four is recombination at best — not invention.
This is not a creativity ritual. Asked for something new, a model regresses toward the mean of its training distribution and dresses the common answer in impressive-sounding language; empirically, LLM assistance even homogenizes ideas across different users (Anderson, Shah & Kreminski 2024 — arXiv:2402.01536). "Novel-sounding" is also not the same as good: creativity evaluations find novelty correlates weakly or negatively with quality and diversity, so it must be scored as its own axis (CreativityPrism — Hou et al. 2025, arXiv:2510.20091). The gate changes the evaluation axis from does this sound impressive to which specific default did this leave, and can it be killed. Divergence without the kill-probe is just confident averaging; the probe is what separates an invention from a nicer-sounding default. Full research basis: references/research-basis.md.
When to use
- The user wants a non-obvious approach, alternative architecture, or design the obvious path does not reach.
- Research directions, product ideas, monetization paths, or agent-skill designs are being generated before a plan is committed.
- The work is at risk of converging on the first plausible answer ("settling too early").
- The user explicitly asks to widen the option space, escape the obvious, or break out of an approach that feels stuck.
When NOT to use
- Factual lookup or current SDK/API/CLI behavior; use
quaere-grounding. - A small implementation edit, or a plan that is already chosen and just needs building; use
quaere-execution. - A bug whose cause is not yet understood; use
quaere-evidence— do not "invent" around an unknown cause. - Cases where the obvious answer is correct and the only cost is wanting it to look clever. Inventing here adds risk, not value.
What ships with it
4 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.
- 10d ago First seen · 176 lines · 163 tokens per session scan A 85381b9014e7
quaere-invention is a skill published in the GitHub repository haru0416-dev/quaere (5 stars, last pushed 1mo ago), licensed MIT. It adds 163 tokens to every session and 2,373 once invoked, about $0.0008 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
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
stage-edit
Intelligent editing of real user-supplied footage—understand it with transcript/OCR/scene/silence/quality/vision evidence, then choose deterministic timeline operations or a constrained semantic AI edit. Trigger for repurpose, montage, cleanup, localization, narration, or local content changes.
gate-control
Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition.…
orchestration
The master program for producing or editing a video end to end — read this at the START of any video task (after video-router), then follow the gates and the per-line steps. Trigger for "make / edit / cut / caption / dub / animate a video"; it sequences the compose / generate / edit lines and the approval gates. Do…
verification-loop
Evidence-before-assertions workflow. Use before claiming work is done, before release, and after any behavior change in scripts/skills/MCP.
kirby-debugging-and-tracing
Diagnoses Kirby rendering/runtime issues using MCP runtime rendering, dump traces, and template/snippet/controller indexes. Use when outputs are wrong, errors occur, or tracing execution paths is required.