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.
npx agentmods add skills/brizzai/fleet/debug-statusnpx skills add brizzai/fleet --skill debug-statusgit clone --depth 1 https://github.com/brizzai/fleetWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00046 | $0.04049 |
| Opus 5 | $0.00023 | $0.02024 |
| Sonnet 5 | $0.00009 | $0.00810 |
| Haiku 4.5 | $0.00005 | $0.00405 |
Grade B, and why
debug-status scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -l "\"$CS\"" ~/.claude/sessions/*.json 2>/dev/null | while read -r f; do How it starts
The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Session Status
Diagnose why a fleet session shows the wrong status. Read-only — report findings and recommend fixes, never edit code.
For architecture details, see reference.md.
Approach
Status flows through a pipeline. Your job is to trace the pipeline and find where it breaks:
Claude Code → hook event → hook-handler binary → status file → fsnotify → UpdateStatus() → TUI
↓
pane capture + conversation-log (JSONL) + Claude session status file — fallback/supplement
At each stage, ask: what does this stage think the status is, and is it correct?
The conversation log (~/.claude/projects/*/<claude_session_id>.jsonl) is a fourth, often-decisive signal: it is appended on real conversation events (tool calls, results, thinking), so unlike the pane it is immune to repaint/spinner/queued-message quirks. Its key use: if the log's last entry is newer than a waiting hook's timestamp, the user already acted and the agent resumed — the session is running even though the hook still says waiting. (It can only confirm running, not waiting: a genuine unanswered prompt and a long-running tool both leave the log static — see Step 2.)
The Claude session status file (~/.claude/sessions/<pid>.json, one per live claude process) is a fifth signal — the only one carrying Claude Code's own status flag (busy / idle / shell) rather than something fleet infers. It's keyed by pid but records sessionId, so you match it to a fleet session by the hook's session_id. Best use: a clean Running-vs-Idle corroborator when the pane is ambiguous. Three sharp limits: (1) trust the value, not statusUpdatedAt — it's event-driven, not a heartbeat, so a busy turn can carry a minutes-old timestamp; gate on whether the pid is alive instead. (2) No waiting value — a permission prompt reads idle/busy here, so it can't source Waiting. (3) Blind to /compact — compaction isn't counted as busy, so it stays idle right through a multi-minute compaction (see Step 2's compaction note). fleet does not consult this file for status detection yet, but the D snapshot does freeze it (claude_session_status.json + a claude_status block in snapshot.json).
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 275 lines · 46 tokens per session scan B a7a6f42108f5
debug-status is a skill published in the GitHub repository brizzai/fleet (52 stars, last pushed 5d ago), licensed Apache-2.0. It adds 46 tokens to every session and 4,049 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…