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/abdullah1854/mcpgateway/debuggingnpx skills add abdullah1854/MCPGateway --skill debugginggit clone --depth 1 https://github.com/abdullah1854/MCPGatewayWhat 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 | $0.00063 | $0.05830 |
| Opus 5 | $0.00032 | $0.02915 |
| Sonnet 5 | $0.00013 | $0.01166 |
| Haiku 4.5 | $0.00006 | $0.00583 |
Grade A, and why
debugging 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 2d 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 — 732 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debugging Protocol (v2 -- Friction-Hardened)
Built from 169 real sessions. Addresses 38 "wrong approach" events, 30 "buggy code" events, 17 "misunderstood request" events. Every rule below exists because it was violated in production.
When This Skill Activates
- "Debug this", "fix this bug", "not working"
- Error messages, stack traces
- "Undefined", "null", "crash", "fails"
- Unexpected behavior
- Performance issues
- Database query returning wrong data
- "Who changed X?" / audit trail questions
STOP-THINK-ACT Protocol (MANDATORY -- Execute Before EVERY Action)
Origin: 38 sessions had "wrong approach" friction -- Claude jumped to the wrong tool, wrong file, or wrong strategy before understanding context. This protocol is non-negotiable.
STOP -- Before writing code, running commands, or choosing an approach:
| Check | Question | If Unclear |
|---|---|---|
| System | Which system/environment is this? Local app? Remote server? Database? | ASK the user. Never assume. |
| Output format | What format does the user want? SQL? Code fix? Plan document? Working code? | ASK if ambiguous. |
| Target file | Am I editing the right file? Local vs remote? Config vs code? Is there a secondary config file? | Verify path before editing. |
| Database | Which database connection? Which server? | Confirm before querying. |
| Branch/Env | Am I on the right branch? Right environment? | Check with git branch or ask. |
THINK -- Before stating conclusions:
| Check | Question | Violation Example |
|---|---|---|
| Evidence | Do I have concrete evidence? | Saying "User X broke this" without a git blame diff |
| Schema | Have I verified actual schemas via MCP? | Assuming a column TransactionDate exists when it's actually TRANSDATE |
| Scope | Am I about to explore when I should execute, or code when asked for a plan? | Spending 45 minutes reading files when user wants a one-line fix |
| Attribution | Am I about to blame someone/something without proof? | "This was probably caused by the last deployment" -- prove it |
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.
- 2d ago First seen · 732 lines · 63 tokens per session scan A c6a6609eaab1
debugging is a skill published in the GitHub repository abdullah1854/MCPGateway (15 stars, last pushed 2mo ago), licensed MIT. It adds 63 tokens to every session and 5,830 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 2026-08-30.
Other skills, from other repositories
xcodebuildmcp-structured-output-review
Use when reviewing XcodeBuildMCP structured output schema changes, schema versioning, manifest outputSchema metadata, and JSON fixture compatibility.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
cortex-automate
Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to…
tabnexus-mcp-evals
Generate, validate, and run isolated Codex-to-TabNexus MCP evaluations with a curated 600-query dataset, executable gold tool labels, safety checks, and best-of-three stability scoring. Use when testing TabNexus MCP tool coverage, Agent behavior, regression quality, destructive-action safety, prompt changes, or a…
compare
Structured comparison of 2+ alternatives with consistent criteria and decision matrix.
maya-shot-export
Pipeline stage — shot-level export: frame ranges, cameras, FBX / Alembic packaging for editorial. Use when packaging shot data for downstream departments. Not for full pipeline publish (maya-pipeline) or scene assembly (maya-scene-assembly).