agentmods.dev

scientific-writing: Agent for Claude Code

.claude/agents/rechercheur.md

rechercheur is an agent for Claude Code from koljaschoepe/scientific-writing. It costs 36 tokens per session (816 once invoked), scanned A, original, MIT.

A literature-research agent searches scholarly databases and services for relevant papers and returns verified candidates as JSON. It can identify preprints, which are research papers shared before formal publication.

In plain words
What is it for?
Use it to find literature for a research question or chapter, check known sources, and produce candidates with details such as titles, authors, dates, and identifiers when verified.
Why use it?
It reduces the need to search several academic services separately and helps avoid invented or unverified bibliographic details. It leaves the final decision about which sources to use to the researcher.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions AGENTS.md.

This is koljaschoepe/scientific-writing's own configuration. It tells Claude Code how to work on scientific-writing itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything scientific-writing configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node .claude/kit/werkzeuge/kandidaten.mjs add - <<'JSON'.

not rated 13repo changed 26d ago A scan 36 tokens original MIT
View source ↗ koljaschoepe/scientific-writing
Reuse

Borrowing it

Nothing to install: this file belongs to koljaschoepe/scientific-writing. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/koljaschoepe/scientific-writing/main/.claude/agents/rechercheur.md
Clone the repo
git clone --depth 1 https://github.com/koljaschoepe/scientific-writing

Made for: Claude Code.

Wrote 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.

agentmods badge for rechercheur

README.md
[![agentmods](https://agentmods.dev/badge/agents/koljaschoepe/scientific-writing/rechercheur/github.svg)](https://agentmods.dev/agents/koljaschoepe/scientific-writing/rechercheur)
Your own site
<a href="https://agentmods.dev/agents/koljaschoepe/scientific-writing/rechercheur"><img src="https://agentmods.dev/badge/agents/koljaschoepe/scientific-writing/rechercheur/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.

agentmods 80×15 button for rechercheur

Your own site · 80×15
<a href="https://agentmods.dev/agents/koljaschoepe/scientific-writing/rechercheur"><img src="https://agentmods.dev/badge/agents/koljaschoepe/scientific-writing/rechercheur.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 816 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.00816
Opus 5.5 $0.00014 $0.00326
Sonnet 5.5 $0.00007 $0.00163
Haiku 4.5 $0.00004 $0.00082

Measured 26d ago against content hash d1140bc08dd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rechercheur scanned grade A with 1 finding 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 26d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

`curl` über Bash als per WebFetch, das liefert die Antwort ungekürzt.
.claude/agents/rechercheur.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rechercheur

Du suchst Literatur und legst Vorschläge im Quellen-Board an. Du entscheidest nicht, was in die Arbeit kommt.

Harte Regeln

Du bekommst AGENTS.md nicht, deshalb hier das Nötige:

  • kurz und warum auf Deutsch, verständlich ohne Fachjargon. Du kannst nicht nachfragen: Unklares gehört in die Rückgabe unter „offen“.
  • Nie eine Quelle, DOI, Autorin oder Jahreszahl erfinden oder ergänzen, die du nicht in einer Antwort eines Dienstes gesehen hast. Keine Schattenbibliotheken.
  • Preprints kennzeichnen (venue: "ChemRxiv (Preprint)").
  • Keine Datei von Hand schreiben. Das Board nur über kandidaten.mjs add.

Vor der Arbeit lesen

  • .arbeit/einstellungen.md (Thema, Fachprofil, Sprache, person.email für mailto)
  • .arbeit/stil.md, Abschnitt „So arbeite ich“ (etwa „verwirft Preprints“, „mag Reviews“)
  • .arbeit/thema/thema.md, falls es schon Kapitel gibt node .claude/kit/werkzeuge/zustand.mjs gliederung (Gliederung aus den Kapiteldateien)
  • Bekanntes: node .claude/kit/werkzeuge/kandidaten.mjs list --kurz (auch verworfene nicht erneut vorschlagen)
  • .claude/kit/leitfaeden/recherche.md (Dienste, Limits, Regeln)

Vorgehen

  1. 2 bis 4 Suchstrings (englisch, bei deutschen Themen zusätzlich deutsch), boolesch, mit Synonymen.
  2. Semantic Scholar suchen. Bei 429 kurz warten, weniger Anfragen. JSON-APIs lieber per curl über Bash als per WebFetch, das liefert die Antwort ungekürzt.
  3. Jede DOI über Crossref prüfen (https://api.crossref.org/works/<doi>?mailto=<email>), Titel muss passen. Ohne prüfbare DOI oder stabile URL verwerfen.
  4. OpenAlex nur mit Umgebungsvariable OPENALEX_API_KEY. Unpaywall für Open-Access-Links.
  5. Schneeball für die 2 bis 3 stärksten Treffer (Referenzen und Zitierungen).
  6. Bewerten: relevanz 1 bis 5, warum in einem Satz, kapitel, markierungen aus kernquelle, methodik, daten, review, kritisch, definition, gegenposition. Mindestens eine Gegenposition suchen, wenn es eine gibt.
  7. Eintragen, alle auf einmal:

Read the full file on GitHub · 63 lines

Changes

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.

  1. 26d ago Changed · -6 lines · -25 tokens per session d1140bc08dd0
  2. 28d ago First seen · 69 lines · 61 tokens per session scan A cb0362bfddb1

Subscribe to this mod's changes

rechercheur is an agent published in the GitHub repository koljaschoepe/scientific-writing (13 stars, last pushed 26d ago), licensed MIT. It adds 36 tokens to every session and 816 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-01.

Claude CodeLaTeXResearchScientificacademic-writingaibachelor-thesismaster-thesis
Related

Other agents, from other repositories

editor

Journal editor who desk-reviews manuscripts, selects two referees with deliberately different dispositions, calibrates to a target journal from .claude/references/journal-profiles.md, and synthesizes an editorial decision (FATAL / ADDRESSABLE / TASTE). Used by /review-paper --peer [journal].

pedrohcgs/claude-code-my-workflow · 64 tokens

domain-reviewer

Substantive domain review for a lecture deck or a manuscript section. Template agent — customize the 5 review lenses for your field. Checks derivation correctness, assumption sufficiency, citation fidelity, code-theory alignment, and logical consistency. Use after content is drafted or before teaching.

pedrohcgs/claude-code-my-workflow · 61 tokens

sim-reviewer

Monte Carlo simulation reviewer. Checks the parts of a simulation study that general R review misses — the assumption regime a run is in, DGP/estimand alignment, replication budget and Monte Carlo standard error, coverage computed against the truth, parallel-seed discipline, and whether headline simulation claims…

pedrohcgs/claude-code-my-workflow · 95 tokens

protocol_architect_agent

Turns a proposal or protocol into confirmed, stage-split screening rules and a screening config before any record is screened.

Imbad0202/academic-research-skills · 27 tokens

reporter_agent

Builds the screening deliverables (log, RIS groups, PRISMA counts, methods draft, corpus handoff) from complete decisions.

Imbad0202/academic-research-skills · 31 tokens

fatal-error-check

Fast pre-review check for fatal errors in LaTeX papers. Launch BEFORE full review agents (paper-critic, domain-reviewer, referee2-reviewer). Binary PASS/FAIL verdict in 15-30 seconds. Checks compilation, placeholders, broken references, number contradictions, and section completeness. Examples: Example 1: user: "Quick…

flonat/flonat-research · 180 tokens