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/sonichi/sutando/call-diagnosticsnpx skills add sonichi/sutando --skill call-diagnosticsgit clone --depth 1 https://github.com/sonichi/sutandoWrote 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/sonichi/sutando/call-diagnostics)<a href="https://agentmods.dev/skills/sonichi/sutando/call-diagnostics"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/call-diagnostics.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.00767 |
| Opus 5 | $0.00000 | $0.00383 |
| Sonnet 5 | $0.00000 | $0.00153 |
| Haiku 4.5 | $0.00000 | $0.00077 |
Grade A, and why
call-diagnostics 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 4d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Call Diagnostics & Repair
Analyze phone call observability data, detect problems, track them across calls, and recommend systematic repairs.
Usage
python3 $CLAUDE_CONFIG_DIR/skills/call-diagnostics/scripts/diagnose.py # last call
python3 $CLAUDE_CONFIG_DIR/skills/call-diagnostics/scripts/diagnose.py --all # all calls + repair recommendations
python3 $CLAUDE_CONFIG_DIR/skills/call-diagnostics/scripts/diagnose.py -t # show timeline
python3 $CLAUDE_CONFIG_DIR/skills/call-diagnostics/scripts/diagnose.py -v # verbose (show detail)
python3 $CLAUDE_CONFIG_DIR/skills/call-diagnostics/scripts/diagnose.py --all --tracker # generate HTML tracker + open
When to use
- After every phone call: run on latest call to detect issues
- Before making fixes: run
--allto see persistent patterns and repair recommendations - Never apply ad-hoc patches — check the repair recommendations first to understand if the problem is persistent and what the systematic fix should be
Detections
- Tool returned too fast (<10ms) — likely error/not-found
- Hallucination — Gemini claimed action state without tool verification
- Inline task via work — recording/screenshot/play delegated instead of inline
- Long delay — >30s between user request and tool execution
- Repeated failures — same tool failing 3+ times
- Timestamp lag — caller speech logged after tool that it triggered
- Wrong tool — Gemini used the wrong tool for the request
- User correction — user explicitly corrected Sutando's behavior
- Unmet expectation — user repeated a request (not understood)
- Auto-invocation — tool called without matching user request
Repair workflow
ALWAYS follow this workflow. Never skip steps.
- Diagnose: run
--all --trackerto see the full picture across all calls - Identify persistent problems: only fix issues that appear across multiple calls. Ignore one-offs.
- Find root cause: ask "why does this happen?" not "how do I patch this instance?"
- Make ONE minimal fix: prefer prompt over code, prefer removing code over adding. If >20 LOC, reconsider.
- Deploy and track: restart servers, then monitor the next 3+ calls in the tracker
- Verify or revert: if the issue count doesn't drop after 2-3 calls, revert and try a different approach
- Never modify source code for call tasks: when a user asks to change something during a call (subtitle color, video edit), use runtime tools (ffmpeg, scripts), not code changes
What ships with it
3 files 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.
- 4d ago First seen · 63 lines · 0 tokens per session scan A 7fe21ee837cc
call-diagnostics is a skill published in the GitHub repository sonichi/sutando (390 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 767 tokens. 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
cc-hooks
Multi-agent hook system: author hooks once as rulesync-canonical hooks.json (HookDefinitionSchema), deploy via superskill install / superskill hook emit to Claude Code, Codex, OpenCode, Pi (pi-hooks), and Gemini CLI. Covers command, prompt, and http hooks, cross-platform event mapping, and safety invariants.
mode
Adopt the lead role for this session: plan work, delegate to executors via relay, review reports, never implement large work directly. Invoke with /relay:mode.
verify
Machine-check an executor's report against its staged reality — TL;DR block well-formed, claimed files actually staged, declared counts cross-checked — stamping MALFORMED / MISMATCH / INCONCLUSIVE / COUNTS-MATCH. Invoke with /relay:verify, or when asked "check that report", "did it really do what it says", "verify X's…
auto
Flip this lead session's autonomous posture: proceed by default on routine in-plan steps instead of asking, or go back to waiting. Invoke with /relay:auto, or when asked to "go autonomous", "stop asking me every time", "just proceed", "turn auto off", "what posture am I in".
collaborating-with-gemini
Delegates coding tasks to Gemini CLI for prototyping, debugging, and code review. Use when needing algorithm implementation, bug analysis, or code quality feedback. Supports multi-turn sessions via SESSIONID.
handoff
Hand this lead session off to a fresh successor. Invoke with /relay:handoff, or when asked to "hand off", "hand this off to a new session", "start a successor lead".