status

A dashboard for all open GitHub pull requests in the current repository, showing their review status, unresolved issues, and blockers.

In plain words
What is it for?
Use it to check open pull requests, review findings, merge readiness, and review-quota status.
Why use it?
It gives you one place to see which changes still need attention and whether anything is preventing a merge.

Skill for Claude CodeCodex

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 skills/auerbachb/claude-code-config/status
Any agent
npx skills add auerbachb/claude-code-config --skill status
Clone the repo
git clone --depth 1 https://github.com/auerbachb/claude-code-config

Made for: Claude Code, Codex.

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,758 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00020 $0.01758
Opus 5 $0.00010 $0.00879
Sonnet 5 $0.00004 $0.00352
Haiku 4.5 $0.00002 $0.00176

Measured 2d ago against content hash 8f6531d45e0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

status 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.

.claude/skills/status/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build a status dashboard of all open PRs in this repo.

Resolve dashboard helpers before listing PRs:

resolve_script() {
  local name="$1" candidate
  for candidate in \
    "$HOME/.claude/skills-worktree/.claude/scripts/$name" \
    "$HOME/.claude/scripts/$name" \
    ".claude/scripts/$name"; do
    if [[ -x "$candidate" ]]; then echo "$candidate"; return 0; fi
  done
  return 1
}
PR_STATE_SH=$(resolve_script pr-state.sh || true)
MERGE_GATE_SH=$(resolve_script merge-gate.sh || true)
CR_HOURLY_SH=$(resolve_script cr-review-hourly.sh || true)
[[ -n "$PR_STATE_SH" ]] || { echo "ERROR: pr-state.sh not found (checked all three paths) — PR dashboard unavailable" >&2; exit 1; }
[[ -n "$MERGE_GATE_SH" ]] || { echo "ERROR: merge-gate.sh not found (checked all three paths) — merge status unavailable" >&2; exit 1; }
[[ -n "$CR_HOURLY_SH" ]] || { echo "ERROR: cr-review-hourly.sh not found (checked all three paths) — review quota status unavailable" >&2; exit 1; }

Invoking-repo scope (issue #687). "in this repo" is load-bearing: the gh pr list below is cwd-repo-scoped by gh, and pr-state.sh --pr N resolves the repo via gh repo view — so the dashboard never surfaces another repo's PRs. /status reads no cross-repo session-state aggregate; if that ever changes, use session-state.sh --session-view (repo-scoped), never --get ..

Steps

Step 1: List open PRs

gh pr list --state open --json number,title,headRefName,updatedAt,author,additions,deletions --limit 50

If no open PRs, say "No open PRs." and stop.

Step 2: For each PR, gather review state

pr-state.sh first (NON-NEGOTIABLE): Before calling gh api .../pulls/{N}/reviews, pulls/{N}/comments, or issues/{N}/comments directly, call pr-state.sh --pr N first and read the cached JSON bundle. All review-state queries in this skill read from the $STATE bundle — do not add inline gh api calls to these three endpoints.

For each open PR, run the shared PR-state helper once per PR. One invocation returns reviews, inline comments, issue comments, unresolved threads, check-runs, and bot status rollups — all derived from the same HEAD SHA:

Read the full file on GitHub · 142 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. 2d ago First seen · 142 lines · 20 tokens per session scan A 8f6531d45e0b

Subscribe to this mod's changes

status is a skill published in the GitHub repository auerbachb/claude-code-config (5 stars, last pushed 3d ago), licensed MIT. It adds 20 tokens to every session and 1,758 once invoked, about $0.0001 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.