Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/sfc-gh-abannerjee/snowgram/snowgram-debugger)<a href="https://agentmods.dev/skills/sfc-gh-abannerjee/snowgram/snowgram-debugger"><img src="https://agentmods.dev/badge/skills/sfc-gh-abannerjee/snowgram/snowgram-debugger/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/sfc-gh-abannerjee/snowgram/snowgram-debugger"><img src="https://agentmods.dev/badge/skills/sfc-gh-abannerjee/snowgram/snowgram-debugger.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 | $0.00055 | $0.02906 |
| Opus 5 | $0.00028 | $0.01453 |
| Sonnet 5 | $0.00011 | $0.00581 |
| Haiku 4.5 | $0.00006 | $0.00291 |
Grade A, and why
snowgram-debugger 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 8d 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 — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SnowGram Autonomous Debug Loop
Architecture: Anthropic SWE-bench Agent Pattern (Jan 2025) + Claude Code Skills (2026) Principle: Minimal scaffolding, maximum model control, deterministic verification
⚡ Entry Point: Route to Correct Sub-Skill
Load this decision tree FIRST before proceeding:
ANALYZE user's bug description:
IF mentions "lane", "badge", "layout", "section", "streaming diagram", "nodes scattered":
→ LOAD $lane-layout-debugger (specialized for layout issues)
→ EXIT this skill
ELIF mentions "agent", "Cortex Agent", "response", "tool call", "semantic model":
→ Continue below with agent-specific patterns
ELIF mentions "test", "npm test", "vitest", "jest", "failing test":
→ Continue below with test debugging patterns
ELSE:
→ Continue below with general SWE-bench pattern
Design Philosophy (2025-2026 Best Practices)
Based on Anthropic's SWE-bench state-of-the-art agent (49% solve rate):
"Our design philosophy was to give as much control as possible to the language model itself, and keep the scaffolding minimal."
| Principle | Implementation |
|---|---|
| Minimal scaffolding | No complex orchestration - single agent with tools |
| Model-driven workflow | Agent decides exploration strategy, not hardcoded |
| Bash + Edit tools | Same tools that achieved SOTA on SWE-bench |
| Context awareness | Uses CLAUDE.md + MEMORY.md for project context |
| Verification-first | Create reproduce script, confirm fix works |
Entry Point: Describe the Bug
$snowgram-debugger
Input: Natural language description of the problem
- "Lane badges not appearing in streaming diagram"
- "Agent returns 'Diagram updated' without code"
- "Tests failing after dependency update"
- "Component not rendering in dark mode"
Autonomous Workflow (SWE-bench Pattern)
The agent follows this suggested approach (but can adapt as needed):
Step 1: Explore Repository Structure
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.
- 8d ago First seen · 416 lines · 55 tokens per session scan A da57e1022ab8
snowgram-debugger is a skill published in the GitHub repository sfc-gh-abannerjee/SnowGram (2 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 2,906 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.