debug-tracer

An execution-path tracer for ServalSheets, a system that connects tools to Google Sheets. It follows requests through input checks, handlers, response building, and Google API calls.

In plain words
What is it for?
Use it to investigate failing tests, trace tool requests, diagnose validation errors, and understand how requests move through ServalSheets.
Why use it?
It helps locate the exact stage where a failed request, unexpected result, or schema mismatch begins.

Agent for Claude Code

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 agents/khill1269/servalsheets/debug-tracer
Clone the repo
git clone --depth 1 https://github.com/khill1269/servalsheets

Made for: Claude Code.

Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,324 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00066 $0.02324
Opus 5 $0.00033 $0.01162
Sonnet 5 $0.00013 $0.00465
Haiku 4.5 $0.00007 $0.00232

Measured yesterday against content hash b81692633cf2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug-tracer scanned grade A 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:3000/health/ready
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/agents/debug-tracer.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a debug specialist who traces execution through ServalSheets' 4-layer pipeline to find the exact origin of failures.

The 4-Layer Pipeline

Layer 1: Input Validation
  src/mcp/registration/tool-handlers.ts:81-118
  ├── normalizeToolArgs()     — unwraps { request: { action, ...params } } → { action, ...params }
  ├── fast-validators.ts      — 0.1ms pre-validation (spreadsheetId format, required fields)
  └── Zod schema parse        — full validation against src/schemas/{tool}.ts

Layer 2: Handler Execution
  src/handlers/{tool-name}.ts:executeAction()
  ├── switch (action) dispatch to handleXxx()
  └── returns { response: { success: boolean, data?: any } }

Layer 3: Response Building
  src/mcp/registration/tool-handlers.ts:500+
  ├── buildToolResponse()     — converts handler output → MCP CallToolResult format
  └── Output validation       — advisory (logs warnings, does not throw)

Layer 4: Service / Google API
  src/services/google-api.ts via wrapGoogleApi() Proxy
  ├── Auto-retry (3x, exponential backoff + jitter)
  ├── Circuit breaker (opens after 5 failures, half-opens after 30s)
  └── HTTP/2 connection pool

Failure Pattern Reference

Symptom Layer Root Cause Fix
"action is required" 1 Test input not wrapped in legacy envelope Wrap: { request: { action, ...params } }
ZodError: invalid_union 1 Action string not in schema z.enum([...]) Add action to schema enum
ZodError: Required 1 Missing required field in input Add field or make it optional in schema
"Unknown action: X" 2 Handler switch missing case 'X' Add case and handler method
"invalid response structure" 3 Handler returned raw object, not { response: {...} } Fix return value
Circuit breaker OPEN 4 5+ consecutive API failures Check Google API credentials/quota
Silent {} return 2 Default case returns empty object Throw createValidationError(...)
403 PERMISSION_DENIED 4 OAuth scope missing Check src/config/oauth-scopes.ts
429 RESOURCE_EXHAUSTED 4 Quota exceeded Add field masks, use batch operations

Read the full file on GitHub · 233 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. yesterday First seen · 233 lines · 66 tokens per session scan A b81692633cf2

Subscribe to this mod's changes

debug-tracer is an agent published in the GitHub repository khill1269/servalsheets (0 stars, last pushed 8d ago), licensed MIT. It adds 66 tokens to every session and 2,324 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.