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-semanticgit 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-semantic)<a href="https://agentmods.dev/skills/haru0416-dev/quaere/quaere-semantic"><img src="https://agentmods.dev/badge/skills/haru0416-dev/quaere/quaere-semantic/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-semantic"><img src="https://agentmods.dev/badge/skills/haru0416-dev/quaere/quaere-semantic.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 | $0.00113 | $0.02403 |
| Opus 5 | $0.00056 | $0.01202 |
| Sonnet 5 | $0.00023 | $0.00481 |
| Haiku 4.5 | $0.00011 | $0.00240 |
Grade A, and why
quaere-semantic 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 9d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Review
Iron Law
No Why without one of: a consulted corroborator marked confident, calibrated reasoning marked plausible, or UNKNOWN — probe: <next step>.
Paraphrasing implementation is not understanding, and a fabricated Why becomes ground truth for the next agent that reads the analysis. Three grounding states, and only these, are acceptable:
confident— a NAMED external corroborator (a test, caller,git blame, spec, or ADR) was actually consulted and supports the claim.plausible— reasoned from the code's own shape but unverified, and explicitly marked as such.UNKNOWN — probe: <step>— the next action that would resolve it.
confident is earned by a consulted corroborator, never by felt certainty. For any unit that mutates state or crosses a trust boundary, if no co-located test, caller, blame, or spec was actually read, the highest marker permitted is plausible. When corroboration is impossible (no tests, no comments, no history, no spec), non-obvious constants and ordering get plausible or UNKNOWN — never an invented intent stated as fact. plausible and UNKNOWN are honest acknowledgments of weaker grounding, not loopholes.
This gate is the load-bearing rule; everything below exists to make the gated Why get produced per unit.
Operational anti-paraphrase test
Analysis is understanding only if it survives a semantic-preserving rewrite of the code (rename a local, swap an equivalent loop form, replace if/else with a ternary, reorder a commutative op). If the rewrite would change any of your answers, that answer is paraphrase — rewrite it to the underlying semantics.
When to use
- Full-file or full-module review where the user wants comprehension, not a checklist.
- Reading an unfamiliar codebase before implementing a feature that touches it.
- Code where intent is non-obvious: clever optimizations, workarounds, hidden invariants.
When NOT to use
- Single-line edits, typos, formatting, quick symbol lookups.
- Code where naming makes intent self-evident and the operational test would not change the answer.
- Bulk mechanical refactors with no semantic risk.
What ships with it
2 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.
- 9d ago First seen · 149 lines · 113 tokens per session scan A 332b4362c893
quaere-semantic is a skill published in the GitHub repository haru0416-dev/quaere (5 stars, last pushed 1mo ago), licensed MIT. It adds 113 tokens to every session and 2,403 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
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.…
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.
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.