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 nWave-ai/nWave --skill nw-investigation-techniquesgit clone --depth 1 https://github.com/nWave-ai/nWaveWrote 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/nwave-ai/nwave/nw-investigation-techniques)<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-investigation-techniques"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-investigation-techniques/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/nwave-ai/nwave/nw-investigation-techniques"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-investigation-techniques.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00021 | $0.00705 |
| Opus 5 | $0.00010 | $0.00352 |
| Sonnet 5 | $0.00004 | $0.00141 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
nw-investigation-techniques 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 7d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigation Techniques
Problem Categorization
Technical Problems
| Category | Sub-Category | Common Symptoms |
|---|---|---|
| System Failures | App crashes, memory leaks, deadlocks, data corruption | Service unavailability, resource exhaustion, integrity errors |
| System Failures | Hardware, network, database, security | Connectivity loss, capacity limits, access failures |
| Performance | Response time: slow queries, latency, algorithmic inefficiency | High p95/p99, user-reported slowness |
| Performance | Throughput: thread pool exhaustion, connection limits, queue backlog | Reduced capacity, growing queues |
| Integration | Internal: component comms, data format, version conflicts | Interface errors, serialization failures |
| Integration | External: third-party availability, API changes, auth failures | Timeouts, contract violations |
Operational Problems
| Category | Common Symptoms |
|---|---|
| Deployment: script failures, config drift, migration errors | Failed releases, environment inconsistencies |
| Monitoring: alerting gaps, backup failures, incident response | Missed incidents, slow recovery |
| Human factors: communication gaps, knowledge silos, skill gaps | Repeated mistakes, slow onboarding |
Evidence Collection
Technical Evidence Sources
Logs: application (timestamp correlation) | system/infrastructure | database | network traces
Metrics: performance/resource utilization | error rates/response time trends | user behavior/transaction patterns | infrastructure health/capacity
Configuration: system/deployment settings | code changes/VCS history (git log, blame) | env vars/dependencies | security/access controls
Evidence Validation
- Cross-reference: verify from multiple independent sources
- Timestamp validation: confirm event sequence accuracy
- Completeness check: identify data gaps/corruption
- Correlation vs causation: distinguish co-occurrence from causation
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.
- 7d ago First seen · 78 lines · 21 tokens per session scan A e110e1f70fff
nw-investigation-techniques is a skill published in the GitHub repository nWave-ai/nWave (610 stars, last pushed 4d ago), licensed MIT. It adds 21 tokens to every session and 705 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
dynamo-interconnect-check
Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a deployment up (especially disagg/multi-node) to confirm the KV transport is correct; use troubleshoot for diagnosing already-failed pods.
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
dynamo-troubleshoot
Diagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail; use recipe-runner/router-starter before this for normal bring-up.
debugging
A structured method for finding and fixing software bugs. It starts by writing a test that reproduces the failure, then investigates its underlying cause before making a small fix.
hk-rca
Interactive Root Cause Analysis enforcer. Guides you through the 7-step RCA protocol: Reproduce, Locate, Hypothesis, Failing Test, Fix, Verify Live, Document. Use when debugging a bug, investigating a failure, or when something unexpected happened. This skill gates each step — it won't let you skip to a fix without…
debug-flow
Systematic debugging workflow. Reproduce the issue, isolate root cause, write a failing test, fix, verify. Use when diagnosing bugs or unexpected behavior.