Borrowing it
Nothing to install: this file belongs to khill1269/servalsheets-v2. 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/khill1269/servalsheets-v2/main/.claude/agents/debug-tracer.mdgit clone --depth 1 https://github.com/khill1269/servalsheets-v2Wrote 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/agents/khill1269/servalsheets-v2/debug-tracer)<a href="https://agentmods.dev/agents/khill1269/servalsheets-v2/debug-tracer"><img src="https://agentmods.dev/badge/agents/khill1269/servalsheets-v2/debug-tracer/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/agents/khill1269/servalsheets-v2/debug-tracer"><img src="https://agentmods.dev/badge/agents/khill1269/servalsheets-v2/debug-tracer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00066 | $0.01710 |
| Opus 5.5 | $0.00026 | $0.00684 |
| Sonnet 5.5 | $0.00013 | $0.00342 |
| Haiku 4.5 | $0.00007 | $0.00171 |
Grade A, and why
debug-tracer 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.
This is a copy
88% identical to debug-tracer — 58 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 177 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 |
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 · 177 lines · 66 tokens per session scan A 15e06470a227
debug-tracer is an agent published in the GitHub repository khill1269/servalsheets-v2 (0 stars, last pushed 4mo ago), licensed MIT. It adds 66 tokens to every session and 1,710 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to debug-tracer, differing in 58 lines, and is treated as a copy.
Other agents, from other repositories
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…