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-prospectgit 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-prospect)<a href="https://agentmods.dev/skills/haru0416-dev/quaere/quaere-prospect"><img src="https://agentmods.dev/badge/skills/haru0416-dev/quaere/quaere-prospect/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-prospect"><img src="https://agentmods.dev/badge/skills/haru0416-dev/quaere/quaere-prospect.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 | $0.00202 | $0.02818 |
| Opus 5.5 | $0.00081 | $0.01127 |
| Sonnet 5.5 | $0.00040 | $0.00564 |
| Haiku 4.5 | $0.00020 | $0.00282 |
Grade A, and why
quaere-prospect 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 1mo 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prospect Probe
Iron Law
No opportunity is proposed as worth building without four things named: the gap it fills (verified to actually exist in the system, not already built and not deliberately out of scope), the beneficiary and the job they are blocked on, the evidence the demand is real rather than assumed, and the smallest probe that would validate or kill it before any build. An opportunity that cannot name all four is a wishlist item, not a proposal — do not present it.
This is not a brainstorming ritual. Asked "what should I build" or "what's missing here", a model regresses toward the mean of its training distribution and emits a plausible-sounding, codebase-agnostic wishlist — add tests, add CI, add dark mode, add a dashboard, add caching — that sounds productive but is tied to no verified gap, names no beneficiary, may already exist or be out of scope, and gives no signal for what is worth building first. LLM assistance even homogenizes the directions it suggests across different users (Anderson, Shah & Kreminski 2024 — arXiv:2402.01536). The gate changes the question from does this sound like useful work to which concrete gap does this fill, who is blocked by it, and how do we know before we build. Proposing from assumption is the failure this skill exists to stop. Full method: references/gap-taxonomy.md and references/research-basis.md.
Stop now — do not present any opportunity you have not checked against the actual system (the capability may already exist, or be a deliberate non-goal); assumption is not evidence. If fewer than the gaps you surface survive the reality gate, loop back and survey more terrain — do not pad with wishlist. Full conditions: ## Stop condition.
When to use
- The user asks what to build next, what feature / tool / product is missing, or where the opportunities are — before any problem is chosen.
- A codebase, domain, or user context needs to be scanned for unmet jobs, friction, or underserved users.
- The work is at risk of answering with a generic feature wishlist instead of a grounded gap.
- The user wants to originate the work item (0→1), not solve a problem already on the table.
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.
- 1mo ago First seen · 167 lines · 202 tokens per session scan A c35b7c2bc952
quaere-prospect is a skill published in the GitHub repository haru0416-dev/quaere (5 stars, last pushed 1mo ago), licensed MIT. It adds 202 tokens to every session and 2,818 once invoked, about $0.0008 per session on Opus 5.5. 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
aitask-note
Send a durable note to an existing aitask — context that task needs which is not itself work. Use when you learn something a task that already exists depends on, such as a stale assumption in its body, a wider blast radius, or a decision that changes its approach.
aitask-pr-import
Create an aitask from a pull request by analyzing PR data and generating a structured task with implementation plan.
aitask-backlog-roadmap
Rank the background-work backlog into a durable, conflict-aware implementation trail — an advisory estimate of what is worth picking up alongside work already in flight.
aitask-contribution-review
Analyze a contribution issue, find related issues, and import as grouped or single task.
implement-spec
A workflow for implementing a complete software specification with acceptance criteria and a dependency graph. It can coordinate independent work items, integrate their changes, run review, and report anything unfinished.
kirby-project-tour
Maps a Kirby project using Kirby MCP tools/resources, including roots, templates, snippets, controllers, models, blueprints, plugins, runtime status, and key config. Use when a user wants a project overview, file locations, or a quick orientation before making changes.