agentmods.dev

PBP: Instructions file for Claude Code

CLAUDE.md

PBP CLAUDE.md is an instructions file for Claude Code from MadGapun/PBP. It costs 24,874 tokens per session, scanned A, original, MIT.

Repository instructions for PBP, a personal job-application portal with a Python MCP server, a React interface, and a SQLite database. They include detailed release notes, version rules, and fixes for matching job opportunities.

In plain words
What is it for?
Use it when changing the job-matching logic, application portal, React frontend, MCP server, database behavior, releases, or scoring and visibility features.
Why use it?
They preserve project-specific decisions about stable releases, beta changes, scoring, visibility, and keyword matching. This helps agents avoid applying fixes only to an unreleased branch or breaking application ranking.

Instructions file for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is MadGapun/PBP's own configuration. It tells Claude Code how to work on PBP 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 PBP configures →

not rated 5repo changed yesterday A scan 24,874 tokens original MIT
View source ↗ MadGapun/PBP
Reuse

Borrowing it

Nothing to install: this file belongs to MadGapun/PBP. 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/MadGapun/PBP/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/MadGapun/PBP

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 PBP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/madgapun/pbp/claude-md.svg)](https://agentmods.dev/instructions/madgapun/pbp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/madgapun/pbp/claude-md"><img src="https://agentmods.dev/badge/instructions/madgapun/pbp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 24,874 This file is loaded in full into every session.
When invoked 24,874 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.24874 $0.24874
Opus 5 $0.12437 $0.12437
Sonnet 5 $0.04975 $0.04975
Haiku 4.5 $0.02487 $0.02487

Measured yesterday against content hash e39aee162836, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

PBP CLAUDE.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 yesterday.

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.

CLAUDE.md · 1,515 lines

How it starts

The opening of the file, as written. The whole thing — 1,515 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PBP — Claude-Code-Memory

Persoenliches Bewerbungs-Portal (PBP). MCP-Server (Python/FastMCP 3.x) + React-Frontend + SQLite. v1.7.30 ist Stable (--latest, 2026-09-04; Kompetenzen aus dem Bestand #971 — Abschluss der Berufsfeld-Recherche. Vier von fuenf Issues erledigt, offen bleibt allein #968 als Nutzerentscheidung). Davor v1.7.29 war Stable (--latest, 2026-09-04; Profil-Erkennung #970 — "Kita" enthielt "ki", eine Erzieherin galt als Tech-Seniorin. Sechs Berufsfelder ergaenzt). Davor v1.7.28 war Stable (--latest, 2026-09-04; Berufsbezeichnungen #969 — derselbe Beruf unter anderem Namen erscheint wieder; dazu ein Nachtrag zu #949, dessen Feldname geraten statt nachgeschlagen war). Davor v1.7.27 war Stable (--latest, 2026-09-02; Kaltstart-Fix #967 — ein frisches Profil fand strukturell nichts. Erster Schritt aus der Berufsfeld-Recherche, siehe Stand-Block). Davor v1.7.26 war Stable (--latest, 2026-09-02; drei Defekte aus der Issue-Durchsicht: Anzeigenalter #949, ehrliche 0-Treffer-Meldung #813, Flaky-Test #767). Davor v1.7.25 war Stable (--latest, 2026-09-02; Wartungsversion — der PII-Guard deckt jetzt auch den MCP-Weg ab, siehe DoD-Punkt 9). Davor v1.7.24 war Stable (--latest, 2026-09-02; sieben Praxis-Befunde #960-#966, Details im Stand-Block unten). Davor v1.7.19 war Stable (--latest, 2026-08-18; zwei totgeglaubte Quellen wiederbelebt — Freelance-Schiene und Engineering-Dienstleister, #925/#926). Davor v1.7.18 war Stable (--latest, 2026-08-18; Nachzug #922/#918-Defekt-2 auf die Praxis-Welle v1.7.17 desselben Tages, Details im Stand-Block unten). Davor v1.7.16 war Stable (--latest, 2026-08-14; erster 1.7er-Release MIT der Sichtbarkeits-Arbeit — bis v1.7.15 lag sie nur auf main. MERKE: Schaufenster-Arbeit ist erst beim Nutzer, wenn sie in der Stable-Linie ist) — Hotfix aus Branch hotfix/v1.7.8 vom Tag v1.7.7: Ausschluss-Keywords matchen strikt (#762; der harte K.o. feuerte fuzzy beim Volltext-Nachpflegen und nullte den Score). MERKE: Fixes, die auch das Stable betreffen, gehoeren in die 1.7-Linie und nicht nur in die 1.8-Beta — die Beta zieht kaum jemand. Davor: v1.7.7 war Stable — v1.7.0 wurde am 2026-06-18 aus beta.108 promotet (User-Wort); v1.7.1 #737-Hotfix, v1.7.2 Windows-Deinstaller (#739), v1.7.3 Matching-Haertung + projekte_anzeigen

  • Schema-Parity (#743/#741/#738), v1.7.4 die Einsteiger-Welle (G17 gefuehrte Kette #744, F24 Ollama-Vorschlaege #745, H17 Melde-Hilfe #746 inkl. Mail-Weg [email protected], B13-Teil-1 #747), v1.7.5 (2026-07-03) Fuehrung & Pflege: G11 Onboarding-Hints im Frontend (#652), Probes adapter-konsistent (#748), Umlaut-Restaurierung profil_umlaute_reparieren (A20/#742), v1.7.6 (2026-07-03) Alltags-Fuehrung (#706/#707/#689/#749), v1.7.7 (2026-07-14) Scoring-Fairness & Praxis-Funde vom 13.07. (#750/#752-#757). Leitlinie des Users: Benutzerfuehrung ist oberste Prioritaet — jeder Flow fuehrt zum naechsten logischen Schritt; Melde-Kultur gehoert zur DNA. v1.6.10 bleibt als aelterer Release verfuegbar. v1.8-Beta-Linie eroeffnet (Planungswelle 2026-07-14, User-Wort): Architektur-Entwurf D1–D5 (Plugins = EXTERNE Prozesse gegen versionierte Ingest-API, kein Code-Loading; Komponenten ≠ Plugins; Pairing statt Discovery) + Beta- Fahrplan in Plan-Roadmap-v18; Beta-Exit-Kriterium v1.8 im Master-Plan. beta.0 = I10 Komponenten-Framework (#751) + E19 Auto-OCR (#750-T2, Schema v49), beta.1 = J1 Ingest-API v1 (#504), beta.2 = J2 Thunderbird
  • J4.1 ics, beta.3 = J5 Newsletter, beta.5 = Welle B (B25/B16/B18-Teil, Schema v52), beta.6 = Hotfix #760 (stderr-Backpressure-Freeze). Betas sind GitHub-Prereleases, --latest bleibt v1.7.7; Hotfix-Pfad: Branch vom Tag v1.7.7. ALLE 25 offenen Issues sind Wellen zugeordnet (Tabelle im Master-Plan → Naechste Schritte): Kern-Wellen B (Quellen: #656 Playwright-Komponente, #735/B25 neu, #627), F (Lokale KI: #669, #714, #632, F16-Rest), D (Bewerbungs-Mehrwert: #740 Referenzen, #452 Interview-Arc), J8 (Branchen-Radar #718/#716/#717, zuletzt); beta.0-Beipack A21/#758, beta.1-Beipack #687/#688 (Snapshots). #671 wurde 2026-07-14 geschlossen (Ebene 0+2 fertig, Ollama-Rest in Welle F). ACHTUNG Schema: v49 ist fuer components (beta.0) reserviert — D24/#740 bekommt die naechste Nummer.

Read the full file on GitHub · 1,515 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. yesterday Changed · +137 lines · +2,642 tokens per session e39aee162836
  2. 6d ago First seen · 1,378 lines · 22,232 tokens per session scan A a665b7b6db37

Subscribe to this mod's changes

PBP CLAUDE.md is an instructions file published in the GitHub repository MadGapun/PBP (5 stars, last pushed 2d ago), licensed MIT. It adds 24,874 tokens to every session, about $0.1244 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.

Pythonbewerbungclaude-desktopjob-searchmcp-serverself-hosted
Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens