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 skills add rudderlabs/rudder-agent-skills --skill rudder-destination-debugginggit clone --depth 1 https://github.com/rudderlabs/rudder-agent-skillsWrote 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/rudderlabs/rudder-agent-skills/rudder-destination-debugging)<a href="https://agentmods.dev/skills/rudderlabs/rudder-agent-skills/rudder-destination-debugging"><img src="https://agentmods.dev/badge/skills/rudderlabs/rudder-agent-skills/rudder-destination-debugging/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/rudderlabs/rudder-agent-skills/rudder-destination-debugging"><img src="https://agentmods.dev/badge/skills/rudderlabs/rudder-agent-skills/rudder-destination-debugging.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Privilege Escalation · line 264 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00048 | $0.02700 |
| Opus 5 | $0.00024 | $0.01350 |
| Sonnet 5 | $0.00010 | $0.00540 |
| Haiku 4.5 | $0.00005 | $0.00270 |
Grade A, and why
rudder-destination-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 11d 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Destination Debugging
This skill teaches how to diagnose and fix event delivery failures between RudderStack and a destination — covering dropped events, auth errors, rate limiting, transformation filters, and warehouse sync failures.
Requires RudderStack MCP connected. See rudder-mcp-setup if not yet configured.
Event Delivery Pipeline
Events travel through four stages before reaching a destination. Each stage can fail independently:
SOURCE SDK
│ events sent
▼
PROCESSOR TRANSFORM
│ maps event to destination format
│ applies user transformations
│ tracking-plan governance (block/log/forward)
▼
ROUTER / BATCH
│ groups events for efficient delivery
│ respects destination rate limits
▼
DATA DELIVERY
│ sends HTTP request to destination API
│ parses response code
├── 2xx ──► delivered ✓
├── 298 ──► filtered (transformation dropped it)
├── 299 ──► suppressed (tracking-plan governance)
├── 429 ──► throttled → retry with backoff
├── 4xx ──► aborted (permanent failure, no retry)
└── 5xx ──► retryable → auto-retry
Debugging Workflow
┌─────────────────────┐
│ Events not at dest? │
└──────────┬──────────┘
│
┌────────────────┼──────────────────┐
▼ ▼ ▼
Source sending? Metrics show Errors present?
(check source failures?
event metrics) (check dest
event metrics)
│ │ │
▼ ▼ ▼
No events at Events sent but Get error messages
source → SDK not delivered → → see error
or connection check error log classification
issue below
Step 1 — Confirm events leave the source
Ask Claude:
"Show me event metrics for source <source-name> over the last hour"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 279 lines · 48 tokens per session scan A c5b1f9159da6
rudder-destination-debugging is a skill published in the GitHub repository rudderlabs/rudder-agent-skills (18 stars, last pushed 6d ago), licensed MIT. It adds 48 tokens to every session and 2,700 once invoked, about $0.0002 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
operating-cadence
Designs the rhythm an organization runs on — which reviews happen weekly, monthly and quarterly, what each one decides, who owns the numbers presented, and how a signal at the front line reaches the people who can act on it. Use this to set up a management operating system, fix a meeting calendar that produces no…
serena
Serena code intelligence — LSP-powered symbol navigation, diagnostics, and targeted code surgery. Activate before complex refactors, cross-file analysis, or when graph tools need symbol-level depth.
diagnose
Structured 6-phase debugging. Build feedback loop first, reproduce deterministically, hypothesize with ranked falsifiable theories, instrument one variable at a time, fix with regression test, cleanup. Use when a bug exists, tests fail unexpectedly, or behavior is wrong and cause is unknown.
fix
Plan-aware auto-fix loop after coding. Runs tests, lint, format, and graph checks. Updates plan task status. Use after execute/tdd.
zoom-out
One-shot module map — go up a layer of abstraction and get a domain-vocabulary module map of the codebase. Use when lost in unfamiliar code, after a long deep-dive session, or when you need to re-orient before planning.
pdlc-perf
A workflow for finding and improving performance problems in a specified backend service or frontend application. It examines areas such as database queries, caching, response times, loading, rendering, and network use, then records its findings in a report.