What is PBP AGENTS.md?

Repository instructions for a German-language personal job-application portal. It helps manage profiles, job searches, applications, document exports, and related analysis.

Use them when changing the portal’s profile, document, job, application, analysis, search, or export features, and when running its test suite.

They give an agent the project structure, technology choices, and testing expectations, reducing the risk of breaking a large application.

PBP AGENTS.md — Instructions file by MadGapun

Install

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.

agentmods

npx agentmods add instructions/madgapun/pbp/agents-md

Clone the repo

git clone --depth 1 https://github.com/MadGapun/PBP

Made for: Codex, OpenCode.

Per session 936 This file is loaded in full into every session.

When invoked 936 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00936	$0.00936
Opus 5	$0.00468	$0.00468
Sonnet 5	$0.00187	$0.00187
Haiku 4.5	$0.00094	$0.00094

Measured 2d ago against content hash 828b54a366a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

PBP AGENTS.md 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 2d 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.

AGENTS.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — PBP (Persönliches Bewerbungs-Portal)

Version: 1.7.0-beta.100 (Stand: 2026-06-09) Detaillierte Doku: README.md, CHANGELOG.md, Wiki Master-Plan

Projektübersicht

PBP ist ein MCP-Server für Claude Desktop, der bei der gesamten Jobsuche und Bewerbung unterstützt — vom Profil-Aufbau über die Stellensuche bis zum Bewerbungstracking.

Sprache: Deutsch Tech-Stack: Python 3.11+, FastMCP 3.x, SQLite (WAL Mode), FastAPI, React 19, Playwright Tests: 1683 Tests (1 bewusst geskippt)

Architektur

Claude Desktop
    │ stdio (MCP Protocol)
    ▼
server.py (FastMCP, ~140 Zeilen)  ◄── Composition Root, registriert Module
    │
    ├── tools/              ◄── 177 MCP-Tools in 11 Modulen
    │   ├── profil.py       — Profilverwaltung, Multi-Profil, Erfassungsfortschritt
    │   ├── dokumente.py    — Dokumenten-Analyse, Extraktion, Profil-Im/Export
    │   ├── jobs.py         — Jobsuche, Stellenverwaltung, Fit-Analyse
    │   ├── bewerbungen.py  — Bewerbungstracking, Status, Statistiken
    │   ├── analyse.py      — Gehalt, Trends, Skill-Gap, Follow-ups
    │   ├── export_tools.py — Lebenslauf/Anschreiben als PDF/DOCX
    │   ├── suche.py        — Suchkriterien und Blacklist
    │   └── workflows.py    — Geführte Workflows
    │
    ├── prompts.py          ◄── 24 MCP-Prompts
    ├── resources.py        ◄── 6 MCP-Resources
    │
    ├── services/           ◄── Service-Layer (profile/search/workspace/email/daily_impulse)
    ├── database.py         ◄── Schema v46, WAL, CASCADE
    │
    ├── dashboard.py        ◄── FastAPI, React-SPA, REST-API
    │
    ├── export.py           ◄── Lebenslauf + Anschreiben (PDF/DOCX)
    │
    └── job_scraper/        ◄── 34 Quellen (6 produktiv, Rest defekt/zurueckgestellt)
        ├── __init__.py     — Dispatcher, Scoring, Deduplizierung
        └── *.py            — Bundesagentur, StepStone, LinkedIn, XING, etc.

Setup & Tests

# Windows: Doppelklick
INSTALLIEREN.bat

# Entwicklung
pip install -e ".[all,dev]"
playwright install chromium

# Tests
python -m pytest tests/ -v

# Dashboard
python start_dashboard.py  # → http://localhost:8200

Read the full file on GitHub · 86 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.

2d ago First seen · 86 lines · 936 tokens per session scan A 828b54a366a6

Subscribe to this mod's changes

PBP AGENTS.md is an instructions file published in the GitHub repository MadGapun/PBP (5 stars, last pushed 5d ago), licensed MIT. It adds 936 tokens to every session, about $0.0047 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.

Documents Research Testing bewerbung claude-desktop job-search mcp-server self-hosted

PBP AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md — PBP (Persönliches Bewerbungs-Portal)

Projektübersicht

Architektur

Setup & Tests

What this file has done since we first saw it

Other instructions, from other repositories

commonly CLAUDE.md

1flowbase AGENTS.md

llm-context.py CLAUDE.md

lobster0 AGENTS.md

VaultysClaw agent-controller.instructions.md

homelab-monitor CLAUDE.md