Hacktoberfest 2026: los issues que los mantenedores marcaron para octubre, abiertos y aptos para principiantes. Explorar issues de Hacktoberfest

[Bug]: inconsistent agent instructions

Cerrado
  • ¿Algo no está bien?
#3,925 2 comentarios 0 reacciones 0 asignados Ver en GitHub

Los mantenedores suelen responder en 1 día

@Tivonsico ya está trabajando en esto.

Desde el 10/10/2026.

  • #4292 de @Tivonsico — abierto

Evaluación

Dificultad
3/5
Tiempo estimado
1-2 días
Aptitud para principiantes
48/100
Tipo de issue
Error
Claridad
Necesita aclaración
Estado de actividad
Activo
Stack tecnológico
python
Área
cli, developer-experience

Línea de trabajo

Compare the AGENTS.md content produced by graphify install with the managed block suggested at https://app.graphify.com/sum/mcp, starting from the installation and initialization entry points. Determine which instructions are authoritative and identify the expected single source or wording; done means the two paths have a documented, non-conflicting result.

Escrito por el modelo de indexación a partir del texto del issue.

Descripción

bug
Pre-flight checks
  • I have checked the Troubleshooting section in the README
What happened?

I initialized with graphify install and this section gets added to AGENTS.md

## graphify

This project has a knowledge graph at graphify-out/ with god nodes, community structure, and cross-file relationships.

When the user types `/graphify`, use the installed graphify skill or instructions before doing anything else.

Rules:
- For codebase questions, first run `graphify query "<question>"` when graphify-out/graph.json exists. Use `graphify path "<A>" "<B>"` for relationships and `graphify explain "<concept>"` for focused concepts. These return a scoped subgraph, usually much smaller than GRAPH_REPORT.md or raw grep output.
- Dirty graphify-out/ files are expected after hooks or incremental updates; dirty graph files are not a reason to skip graphify. Only skip graphify if the task is about stale or incorrect graph output, or the user explicitly says not to use it.
- If graphify-out/wiki/index.md exists, use it for broad navigation instead of raw source browsing.
- Read graphify-out/GRAPH_REPORT.md only for broad architecture review or when query/path/explain do not surface enough context.
- After modifying code, run `graphify update .` to keep the graph current (AST-only, no API cost).

on the web app https://app.graphify.com/sum/mcp these instructions are suggested to be copied into AGENTS.md

<!-- graphify-rules-start (managed by `graphify init`) -->
## Use Graphify before grep

This repository is indexed by Graphify: a code graph over its call, dependency, and test structure, exposed through a connected Graphify MCP server. Before reaching for grep or reading files, use the Graphify tools your MCP client lists (their exact names and descriptions are in the server's tool list) for what the graph knows and a text search does not:

- find where a symbol, function, or class is defined (instead of grepping for it)
- understand how something works, or where a behavior is handled
- find who calls a function, or what it calls
- see what a change affects (its blast radius) and which tests cover it
- map a file's dependencies and dependents

Fall back to grep or file reads only for what the graph does not model: literal string or comment matches, non-indexed files, or reading a file you have already located. If no Graphify tools are listed, check the MCP server connection.
<!-- graphify-rules-end -->

Which one has precendence, is the correct or better one ?

Steps to reproduce
see above
Error output or graph output
not tested
Graphify version

0.9.71

Operating System

Linux

Python Version

3.13

Installation Method

uv tool install (recommended)

Additional Environment Details

python version : 3.14.7

Additional context

No response

Lenguaje dominante
Python
Estrellas
124k
Forks
11.9k
Sin PR fusionados en 30 d

Preparar el entorno

Este proyecto no incluye contenedor de desarrollo, Dockerfile ni guía de contribución, así que la configuración corre por tu cuenta: empieza por su README y consulta nuestra guía para la primera contribución para los pasos generales.

Primeros pasos

  1. Lee el issue completo y luego la guía de contribución del proyecto.
  2. Comenta en el issue que vas a ocuparte — evita que dos personas hagan lo mismo.
  3. Haz un fork del repositorio y trabaja en una rama.
  4. Abre un pull request que haga referencia al número del issue.

Más de Graphify-Labs/graphify

Todos los issues de Graphify-Labs/graphify

Issues similares

Más issues de Python

Recibe los nuevos issues en tu correo

Un resumen breve de issues de GitHub para principiantes.