Hacktoberfest 2026: le issue che i maintainer hanno segnato per ottobre, aperte e adatte ai principianti. Sfoglia le issue Hacktoberfest

Add CLAUDE.md to provide agent context for code and triage tasks

Aperta Adatta ai principianti
#965 1 commento 0 reazioni 0 assegnatari Vedi su GitHub

I maintainer di solito rispondono entro 1 giorno

Nessuno ha ancora preso questa issue.

Valutazione

Difficoltà
2/5
Tempo stimato
1-3 ore
Idoneità per principianti
72/100
Tipo di issue
Documentazione
Chiarezza
Abbastanza chiara
Stato di attività
Attiva
Stack tecnologico
go

Direzione di ricerca

Inizia leggendo .fullsend/harness/code.yaml e .fullsend/harness/triage.yaml, quindi esamina i controlli di build, test, lint, format e verify-docs a cui si fa riferimento nell’issue e nella PR #964. Aggiungi una CLAUDE.md concisa nella root, di meno di 60 righe, che copra le convenzioni richieste per il progetto, il workflow, i test e le PR, e assicurati che documenti i comandi elencati e le aspettative di validazione.

Scritto dal modello di indicizzazione a partire dal testo della issue.

Descrizione

ready-for-triage

What happened

PR #964 was a human-authored change that required no agent involvement. However, reviewing the repo's fullsend configuration revealed that while the repo has a mature agent setup — 6 roles enabled (triage, coder, review, fix, retro, prioritize), Jira integration polling every 5 minutes for ROSAENG issues with component = osdctl, custom sandbox network policies, and issues actively labeled ready-to-code (#943, #941) — it has no CLAUDE.md, .claude/ directory, or AGENTS.md file. The harness configs at .fullsend/harness/code.yaml and .fullsend/harness/triage.yaml extend upstream fullsend-ai/[email protected] but provide no repo-specific context beyond Jira credentials.

What could go better

When code or triage agents are dispatched for this Go CLI project, they currently have no repo-specific guidance about build commands (make build, make test, make lint, make format), project structure, testing conventions, or coding standards. The agents must discover these through exploration, which increases token cost, rework risk, and time to resolution. This is high-confidence — the repo clearly uses agents for real work (Jira-driven triage, ready-to-code labeled issues), and the absence of context files is a straightforward gap. The CI workflow files modified in this PR show that the project uses Prow for CI (build, format, lint, test, verify-docs checks), GoReleaser for releases, and COPR for RPM builds — all context that would help agents navigate the project.

Proposed change

Create a CLAUDE.md file at the repository root covering at minimum:

  1. Build and test commands — make build, make test, make lint, make format, make verify-docs (derived from the Prow CI checks visible in the PR status checks).
  2. Project overview — Go CLI tool (osdctl) for OpenShift Dedicated cluster operations, built with GoReleaser.
  3. Code structure — key directories, command registration pattern, and how new commands are added.
  4. Testing conventions — unit test expectations, any integration test patterns.
  5. PR conventions — Prow-based review process using OWNERS files and /lgtm + /approve commands; merge handled by openshift-merge-bot.

Keep the file concise (under 60 lines per platform guidelines). Focus on information that helps agents write correct code on the first attempt — build commands, test commands, and common pitfalls.

Validation criteria

After CLAUDE.md is added, the next 3 code agent runs on this repo should: (1) use the documented build/test commands without needing to discover them through exploration, (2) produce PRs that pass make lint and make format on the first commit without requiring fix agent intervention, and (3) show reduced token usage in the exploration phase compared to prior code agent runs (if any exist for baseline comparison).


Generated by retro agent from https://github.com/openshift/osdctl/pull/964

Lingua principale
Go
Stelle
47
Fork
142
Merge medio
1g 10h
PR unite (30g)
11

Preparare l'ambiente

Non abbiamo ancora controllato i file di configurazione di questo progetto. Parti dal suo README e consulta la nostra guida al primo contributo per i passaggi generali.

Come iniziare

  1. Leggi tutta la issue e poi la guida ai contributi del progetto.
  2. Commenta sulla issue per dire che te ne occupi tu — evita che due persone facciano lo stesso lavoro.
  3. Fai un fork del repository e lavora su un branch.
  4. Apri una pull request che faccia riferimento al numero della issue.

Altre issue di openshift/osdctl

Tutte le issue di openshift/osdctl

Issue simili

Altre issue su Go

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.