agentleFS
Ryan-M-FrankRyan-M-Frank/volley/skills/diagnose/SKILL.md

diagnose

Skill2 starsChanged 5 months agoApache-2.0View on GitHub

Diagnose the Volley environment in one shot - Codex CLI and its non-interactive mode, the platform terminal, and the per-repo lock state. Use when setup misbehaves or before starting a session in a new repo.

  • Installs packages

193 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use zoom-out, to-prd and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • victorgarciaesgiSkill

    zoom-out

    Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

    Also in 61 projects that use this

  • GoogleSkill

    to-prd

    Turn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

    Also in 56 projects that use this

  • GoogleSkill

    to-issues

    Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.

    Also in 53 projects that use this

  • simo97Skill

    edit-article

    The user will invoke this skill to help them edit an article.

    Also in 17 projects that use this

  • simo97Skill

    write-a-skill

    Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

    Also in 44 projects that use this

  • AnasX7Skill

    setup-pre-commit

    Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

    Also in 27 projects that use this

  • +4 more from simo97

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 175 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Codex CLI present: Run codex --version. PASS if it prints a version >= 0.156.

    line 12
  2. Very specific:

    Per-repo lock state: If .volley/STATE exists, report it and whether the named process is alive.

    line 35
  3. Very specific:

    Saved-session integrity: If .volley/local.json has role thread/session IDs, report them as present (never print secrets).

    line 66

“Common” is measured: kept by at least 6 in 10 of the 175 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/volley:diagnose

One-shot diagnosis of whether Volley is wired up correctly here. Run each check, print a [PASS]/[FAIL]/[WARN] line, and end with a remediation list for anything not green.

Steps for Claude

  1. Codex CLI present. Run codex --version. PASS if it prints a version >= 0.156; FAIL otherwise (remedy: npm install -g @openai/codex).
  2. Codex runs non-interactively. Run codex exec --help; PASS if it succeeds, FAIL otherwise (remedy: update Codex with npm install -g @openai/codex). Then WARN if any .mcp.json in this repo still registers codex mcp-server (remedy: remove that entry - Codex 0.156 removed the command and Volley no longer uses MCP). Do not make a model call here.
  3. Platform terminal available. Detect the OS and check for a usable terminal launcher:
    case "$(uname -s)" in
      Darwin*) command -v osascript >/dev/null && echo "[PASS] macOS terminal (osascript)" || echo "[FAIL] osascript missing" ;;
      Linux*)  { command -v gnome-terminal || command -v kitty || command -v tmux; } >/dev/null \
                 && echo "[PASS] Linux terminal (gnome-terminal/kitty/tmux)" \
                 || echo "[FAIL] no gnome-terminal/kitty/tmux - install one or use VOLLEY_PLATFORM=tmux" ;;
      MINGW*|MSYS*|CYGWIN*) command -v wt >/dev/null && echo "[PASS] Windows Terminal (wt)" || echo "[FAIL] wt missing - install Windows Terminal" ;;
      *) echo "[WARN] unrecognized OS; set VOLLEY_PLATFORM=tmux for the universal fallback" ;;
    esac
  4. Plugin assets intact. Confirm the bundled scripts resolve:
    for f in scripts/lib.sh scripts/codex-exec.sh scripts/spawn-codex.sh scripts/platforms/windows.sh scripts/platforms/macos.sh scripts/platforms/linux.sh scripts/platforms/tmux.sh; do
      [ -f "${CLAUDE_PLUGIN_ROOT}/$f" ] && echo "[PASS] $f" || echo "[FAIL] missing $f"
    done
  5. Per-repo lock state. If .volley/STATE exists, report it and whether the named process is alive; otherwise note the repo isn't initialized:
    if [ -f .volley/STATE ]; then
      active=$(grep -E '^ACTIVE=' .volley/STATE | cut -d= -f2)
      task=$(grep -E '^TASK=' .volley/STATE | cut -d= -f2)
      pid=$(grep -E '^PID=' .volley/STATE | cut -d= -f2)
      echo "[INFO] lock: ACTIVE=$active TASK=$task PID=$pid"
      if [ -n "$pid" ] && [ "$pid" != "0" ]; then
        kill -0 "$pid" 2>/dev/null && echo "[INFO] named PID $pid is alive" \
          || echo "[WARN] named PID $pid is dead - lock may be stale; run /volley:unlock if it's stuck"
      fi
    else
      echo "[WARN] .volley/ not initialized here - run /volley:setup"
    fi
  6. Continuity + model config (v0.2). Non-mutating, and no model turn unless the user explicitly asks for a live model probe.
    • Config parses & validates. Read .volley/config.json (parse yourself - no jq). PASS if valid JSON with a known version; WARN if absent (= defaults in effect); FAIL if present but malformed or unknown version. Report the resolved review/implementation model + reasoningEffort (show inherit as "Codex default"). Do not call a model to check availability here - note that model validity is confirmed by the /volley:setup smoke call (or an opt-in --live probe).
    • Repository identity. Compare .volley/local.json repository to the live repo:
      . "${CLAUDE_PLUGIN_ROOT}/scripts/lib.sh"
      if [ -f .volley/local.json ]; then
        # extract stored root/remote in-host (JSON), then:
        volley_repo_identity_matches "<stored_root>" "<stored_remote>" \
          && echo "[PASS] repo identity matches live checkout" \
          || echo "[WARN] repo identity mismatch - stored session IDs will be ignored (fresh session + file rehydration)"
      else
        echo "[INFO] no .volley/local.json yet - run /volley:setup"
      fi
    • Context files. For each context.required file, PASS if present / FAIL if missing (names the file). For context.optional, list present vs skipped.
    • Saved-session integrity. If .volley/local.json has role thread/session IDs, report them as present (never print secrets); WARN if the file is unreadable/corrupt.
    • Managed checkpoint. PASS if .volley/CHECKPOINT.md exists and still contains both volley:managed markers; WARN otherwise.
  7. Summary. Print a final Volley diagnose: N passed, M warnings, K failures line and, for each FAIL/WARN, the one-line remedy.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.