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-executiongit 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-execution)<a href="https://agentmods.dev/skills/haru0416-dev/quaere/quaere-execution"><img src="https://agentmods.dev/badge/skills/haru0416-dev/quaere/quaere-execution/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-execution"><img src="https://agentmods.dev/badge/skills/haru0416-dev/quaere/quaere-execution.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 | $0.00130 | $0.03642 |
| Opus 5.5 | $0.00052 | $0.01457 |
| Sonnet 5.5 | $0.00026 | $0.00728 |
| Haiku 4.5 | $0.00013 | $0.00364 |
Grade A, and why
quaere-execution 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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execution Loop
Iron Law
No implementation success claim without fresh verification evidence and a reviewed diff that maps every changed line to the authorized scope.
This is not a paperwork rule. Implementation drift usually happens after the edit: the agent sees a green-looking result, forgets which requirement justified each change, and declares done before studying the actual diff. The loop is Plan → Do → Study → Act: predict what will prove the unit, make the smallest scoped edit, compare the observed result to the prediction, then either fix, split, or hand off. A passing broad suite is useful, but it does not replace the targeted check or the scope review.
When to use
- The user asks to implement, build, finish, apply a plan, execute a TODO list, refactor, add tests, or address review feedback.
- The work has more than one meaningful step, touches several files, or needs targeted and final checks.
- A confirmed claim from
quaere-evidence, constraints fromquaere-grounding, or invariants fromquaere-semanticare ready to implement.
When NOT to use
- Trivial one-line edits, typo/format-only changes, pure explanations, or single command requests.
- Unclear bugs, flaky tests, risky review claims, security-sensitive causes, or production-side effects whose cause is not confirmed; use
quaere-evidencefirst (or thequaere-auditextension for property-driven security work, if installed). - Current SDK/API/CLI behavior that has not been anchored; use
quaere-groundingfirst.
Handoff triggers (when to switch out)
Stop and hand off when the blocker is no longer implementation:
- Cause of a failing test or regression is unclear →
quaere-evidence. - Implementation depends on current SDK / API / CLI / cloud / advisory behavior that is not yet anchored →
quaere-grounding. - Existing module intent or invariants are unclear →
quaere-semantic. - Security properties or auth / tenancy / parser / concurrency / crypto / payment / sandbox risks come up → stop before patching beyond a confirmed fix. If the
quaere-auditextension is installed, hand off to it; otherwise flag the security risk and escalate to the user.
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.
- 1mo ago First seen · 270 lines · 130 tokens per session scan A ff660bfa5071
quaere-execution is a skill published in the GitHub repository haru0416-dev/quaere (5 stars, last pushed 1mo ago), licensed MIT. It adds 130 tokens to every session and 3,642 once invoked, about $0.0005 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
task-workflow
Shared implementation workflow for task-based skills, with profile-check sites wrapped in Jinja conditionals.
task-workflow
Shared implementation workflow for task-based skills, with profile-check sites wrapped in Jinja conditionals.
task-workflow
Shared implementation workflow for task-based skills, with profile-check sites wrapped in Jinja conditionals.
aitask-pickrem-remote
Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls.
aitask-pickrem-remote
Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls.
aitask-explorechat
Chat-native explore flow for a bug report — machine-spawned by the chatlink gateway, every decision routed through the file-spool Q&A relay instead of AskUserQuestion, ending in a task-creation payload.json. Not a user task command.