Borrowing it
Nothing to install: this file belongs to yaodub/cast. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yaodub/cast/main/.claude/skills/cast-debug/SKILL.mdgit clone --depth 1 https://github.com/yaodub/castWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yaodub/cast/cast-debug)<a href="https://agentmods.dev/skills/yaodub/cast/cast-debug"><img src="https://agentmods.dev/badge/skills/yaodub/cast/cast-debug/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yaodub/cast/cast-debug"><img src="https://agentmods.dev/badge/skills/yaodub/cast/cast-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 64 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00138 | $0.02056 |
| Opus 5.5 | $0.00055 | $0.00822 |
| Sonnet 5.5 | $0.00028 | $0.00411 |
| Haiku 4.5 | $0.00014 | $0.00206 |
Grade A, and why
cast-debug 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cast — diagnosis
You are Claude Code in Cast's debugging lane. The operator wants you to figure out why something happened (or didn't). Read first; don't propose fixes until the cause is named.
Scope
Argument: <folder> (optional).
- With folder → focus on one agent. Read its
state/,home/,sessions/first; consult the gateway and host server logs second. - Without folder → server-scope problem. The gateway, host logs, and code under
packages/cast/are the primary read surface.
If the user's question doesn't make either scope obvious, ask which agent (or "across the fleet") before diving in.
Two audiences, same read surface
Most debug sessions fall into one of two shapes. The read surface is the same; the question filters which layer you read first.
| Question shape | Read first | Then |
|---|---|---|
| Agent misbehavior — "why did the agent say X?" / "why did it call tool Y with those args?" / "why didn't it produce output?" | Session transcript, agent-runner debug log, agent.db message_log |
Gateway DB (only if delivery is also in question), host logs (for ACL blocks or lifecycle events) |
| Cast-server / pipeline — "why isn't this message arriving?" / "the container won't start" / "ACL is rejecting something it shouldn't" / "the scheduler isn't firing" | Gateway DB, host server logs, packages/cast/src/... source |
agent.db, agent-runner log (only after pipeline cause is ruled out) |
Don't pick one and stick to it. The cause often crosses the boundary — an agent that produces no output (misbehavior) might be reacting to an unexpected stdin-message piped in by a self-loop (pipeline).
Read this first — authoritative
packages/cast/manuals/dev/debugging.md is the reference for this skill. It covers:
- The full message lifecycle (transport → gateway → bus → manager → conversation → container → SDK → output → transport).
- Delivery semantics (at-most-once, fire-and-forget, the abnormal-exit retry loop).
- Where to look, ordered by usefulness (gateway DB, agent message log, host logs, agent-runner debug log, session transcripts, scheduled tasks).
- The cross-check matrix ("did the agent spawn with my new mount?", "did the ACL block the reply?", etc.).
- Common scenarios (no response, wrong output, intermediate leaks, scheduled task fires but content missing, lifecycle messages, container tool failures, SDK turn never completes, cross-agent request/response issues).
- The reset patterns (forcing a fresh session without restarting the server).
- The bug-report format — the mechanism-as-proof standard, environment block, redaction discipline, and template — for filing a Cast software defect upstream.
- File locations and log levels.
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.
- 2mo ago First seen · 95 lines · 138 tokens per session scan A 8971c0cf1d62
cast-debug is a skill published in the GitHub repository yaodub/cast (41 stars, last pushed 2mo ago), licensed MIT. It adds 138 tokens to every session and 2,056 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
oracle
Oracle second-model review: bundle prompts/files, debug, refactor, design.
skill-repair
Diagnose and fix failing or degraded skills automatically - systemic-first triage, per-category playbooks, and a verification plan.
self-improve
Improve the agent itself, or audit its recent performance - better skills, prompts, workflows, and config, plus a quality/reliability/memory-hygiene review of what it did and what failed.
posthog-errors
Weekly cross-project error overview from PostHog - enumerates every project the OAuth grant covers, pulls the last 7 days of error-tracking issues per project, ranks them by impact, flags what's new vs ongoing, and sends one digest with per-project totals, the top issues, and a clickable link to a full committed…
aeon-doctor
Static config-correctness linter for this instance - catches the silent-failure class (unquoted schedules, duplicate keys, unconfigured skills, mode typos, broken requires/MCP refs) that no run-based health skill can see. Notifies only on problems.
manage-skills
A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.