Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/greglas75/zuvonpx agentmods add skills/greglas75/zuvo/debugWrote 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/greglas75/zuvo/debug)<a href="https://agentmods.dev/skills/greglas75/zuvo/debug"><img src="https://agentmods.dev/badge/skills/greglas75/zuvo/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/greglas75/zuvo/debug"><img src="https://agentmods.dev/badge/skills/greglas75/zuvo/debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 MCP Rug Pull · line 419 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 420 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00055 | $0.07618 |
| Opus 5.5 | $0.00022 | $0.03047 |
| Sonnet 5.5 | $0.00011 | $0.01524 |
| Haiku 4.5 | $0.00006 | $0.00762 |
Grade A, and why
debug 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 today.
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.
1. Reproduce with curl or the test runner against the endpoint How it starts
The opening of the file, as written. The whole thing — 687 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zuvo:debug — Structured Bug Investigation
A disciplined five-phase process for turning a bug report, error message, or unexpected behavior into a confirmed root cause, verified fix, and permanent regression test.
Scope: Any bug, error, or unexpected behavior that needs investigation.
Out of scope: Code quality sweeps (use zuvo:code-audit), general review (use zuvo:review), performance problems without a specific bug (use zuvo:performance-audit).
Argument Parsing
Parse $ARGUMENTS to determine the starting phase:
| Input | Starting point |
|---|---|
| (empty) | Ask the user: "Describe the issue. Share the error message, stack trace, or explain what is happening." |
| Error message or stack trace | Phase 1.5 (Minimal Reproduction) -- verify the error is reproducible before narrowing |
| Code snippet or file reference | Phase 3 (Diagnose) -- read the code, trace the execution path |
| Description like "why does X" or "X is broken" | Phase 1 (Reproduce) -- gather context before proceeding |
--regression flag, or words like "bisect", "regression", "this used to work" |
Phase R (Regression Bisect) -- automated git bisect to find the breaking commit |
Environment Compatibility
Dispatch follows ../../shared/includes/execution-policy.md through env-compat. Reuse existing
authorization within that policy; session restrictions take precedence. Run each required gate
and report its actual independence or an unmet requirement.
Read ../../shared/includes/env-compat.md for agent dispatch patterns, path resolution, and progress tracking across all supported platforms.
CodeSift Integration
Read ../../shared/includes/codesift-setup.md for the full initialization sequence.
Key tools for debugging:
| Phase | Task | CodeSift tool | Fallback |
|---|---|---|---|
| 2 | Identify recent symbol-level changes | changed_symbols(repo, since="HEAD~5") |
git log --oneline + git diff |
| 2 | Compact change summary | diff_outline(repo, since="HEAD~5") |
git diff --stat |
| 2 | Blast radius of recent changes | impact_analysis(repo, since="HEAD~5", depth=2) |
Grep for imports of changed files |
| 3 | Trace callers/callees of buggy function | trace_call_chain(repo, symbol_name, direction, depth=3) |
Repeated Grep for function name |
| 3 | Understand buggy function with imports and siblings | get_context_bundle(repo, symbol_name) |
Read the entire file |
| 3 | Find where an error is thrown | search_text(repo, query="error message", regex=true) |
Grep |
| 3 | Read multiple functions along the call path | get_symbols(repo, symbol_ids=[...]) |
Multiple Read calls |
| 3 | File structure around the bug | get_file_outline(repo, file_path) |
Read the file |
| Any | Batch 3+ lookups | codebase_retrieval(repo, queries=[...]) |
Sequential Grep/Read |
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.
- today Changed 72011677f42f
- 4d ago Changed · +2 lines 3d48cb373354
- 6d ago Changed · +2 lines b5807c3dba14
- 1mo ago Changed · -2 lines 85ced68b9197
- 1mo ago First seen · 685 lines · 55 tokens per session scan A 0b80fcf3d682
debug is a skill published in the GitHub repository greglas75/zuvo (8 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 7,618 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
ring:detecting-goroutine-leaks
Detecting goroutine leaks in Go: greps for goroutine patterns, audits goleak coverage (VerifyTestMain/VerifyNone), runs goleak, and dispatches ring:backend-go to fix leaks and add regression tests. Use after implementation or during review when code spawns goroutines or a leak is suspected. Runs before…
ring:test-driven-development
Enforcing the RED-GREEN-REFACTOR loop: write one failing test and watch it fail, write minimal code to pass, then refactor green. Use when starting implementation of a new feature or bugfix, or writing any new production code. Requires pasted failure output as proof of RED; code written before its test must be…
ai-agent-bench
Compare Claude Code and Codex on the same code task, with isolated worktrees, common checks, time, and cost.
create-test
Define or implement regression proof: test strategy, black-box or integration tests, KPIs, thresholds, audits, or missing tests.
refactor
Audit an existing project against its standards and apply selected improvements while preserving behavior.
wrap-up-branch
Finish a feature branch: add missing tests, review and fix the code, align docs, then merge only after explicit confirmation.