Borrowing it
Nothing to install: this file belongs to ystreibel/logseq-wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ystreibel/logseq-wiki/main/.skills/wiki-research/SKILL.mdgit clone --depth 1 https://github.com/ystreibel/logseq-wikiWrote 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/ystreibel/logseq-wiki/wiki-research)<a href="https://agentmods.dev/skills/ystreibel/logseq-wiki/wiki-research"><img src="https://agentmods.dev/badge/skills/ystreibel/logseq-wiki/wiki-research/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/ystreibel/logseq-wiki/wiki-research"><img src="https://agentmods.dev/badge/skills/ystreibel/logseq-wiki/wiki-research.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 | $0.00083 | $0.01517 |
| Opus 5.5 | $0.00033 | $0.00607 |
| Sonnet 5.5 | $0.00017 | $0.00303 |
| Haiku 4.5 | $0.00008 | $0.00152 |
Grade A, and why
wiki-research 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 2mo 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Research — Recherche Autonome Multi-Round
Tu exécutes une boucle de recherche autonome sur un sujet, synthétises ce que tu trouves, et déposes les résultats dans le wiki Logseq comme connaissance permanente.
Avant de commencer
- Lire
~/.logseq-wiki/config(ou.envlocal, premier trouvé) →LOGSEQ_VAULT_PATH - Lire
$LOGSEQ_VAULT_PATH/wiki/_master-index.mdpour comprendre ce qui est déjà dans le wiki — ne pas re-rechercher des sujets bien couverts - Lire
$LOGSEQ_VAULT_PATH/wiki/_log.md(hot context) si disponible
Confirmer le sujet de recherche avec l'utilisateur s'il est ambigu. Puis procéder.
Configuration de recherche (optionnelle)
Si $LOGSEQ_VAULT_PATH/wiki/_meta/research-config.md existe, le lire et appliquer :
- Préférences de sources (ex: préférer académique, éviter certains domaines)
- Domaines à ignorer
- Ajustements de scoring de confiance
- Contraintes spécifiques au sujet
Round 1 — Survey Large
Objectif : Cartographier le sujet.
- Décomposer le sujet en 3-5 angles distincts
- Pour chaque angle, lancer 2-3 requêtes WebSearch avec des formulations variées
- Pour les 2-3 meilleurs résultats par angle, fetcher le contenu
- De chaque page fetchée, extraire :
- Claims clés — ce que la source dit explicitement
- Concepts — idées, termes, frameworks introduits
- Entités — outils, personnes, organisations mentionnés
- Contradictions — là où les sources se contredisent
Suivre ce qui est couvert et ce qui manque au fur et à mesure.
Round 2 — Combler les lacunes
Objectif : Fermer les trous du Round 1.
Relire ce que le Round 1 a produit :
- Quelles questions les sources ont-elles soulevées sans répondre ?
- Où les sources se contredisent-elles ?
- Quels angles ont été peu couverts ?
Lancer jusqu'à 5 recherches ciblées sur ces lacunes. Préférer les sources primaires, la documentation officielle, les analyses de référence.
Mettre à jour le working set. Mettre à jour la liste de contradictions.
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.
- 2mo ago First seen · 172 lines · 83 tokens per session scan A 8b78f58843cb
wiki-research is a skill published in the GitHub repository ystreibel/logseq-wiki (5 stars, last pushed 11d ago), licensed MIT. It adds 83 tokens to every session and 1,517 once invoked, about $0.0003 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.
wiki-research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wiki-researchystreibel/logseq-wiki | Skill | 5 | 11d ago | MIT | A | 83 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |