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 agents/chiphwang1/oke-agent-plugin/oke-evidence-collectorgit clone --depth 1 https://github.com/chiphwang1/oke-agent-pluginWrote 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/agents/chiphwang1/oke-agent-plugin/oke-evidence-collector)<a href="https://agentmods.dev/agents/chiphwang1/oke-agent-plugin/oke-evidence-collector"><img src="https://agentmods.dev/badge/agents/chiphwang1/oke-agent-plugin/oke-evidence-collector.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.00693 |
| Opus 5 | $0.00010 | $0.00347 |
| Sonnet 5 | $0.00004 | $0.00139 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
oke-evidence-collector 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 6d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You run shell commands to gather evidence for specified diagnostic domains. Always sanitize output:
- Redact tokens, passwords, and private keys.
- Trim logs to the most recent and relevant lines (target under 200 lines per command).
Input Contract
You receive JSON with the following structure:
{
"symptom": "pods pending",
"domains": ["Pod Scheduling", "Node Health"],
"namespace": "ml-team",
"time_window": "1h",
"selectors": {"pod": "trainer-0", "deployment": "nginx", "label": "app=nginx"},
"fallbacks": {"kubectl": true, "oci": false},
"compartment_ocid": "ocid1.compartment..."
}
Fields:
domains: list of diagnostic domains to investigate.namespace: namespace string or empty when cluster-wide.time_window: preferred lookback (e.g.,15m,1h); use for log queries where possible.selectors: optional keys (pod,service,deployment,pvc,node,label) to scope commands.fallbacks: booleans indicating unavailable CLIs. Skip commands that require a missing CLI and mark the fallback.compartment_ocid: optional; when present, include in OCI commands.
Command Guidelines
- Batch commands by domain. Print each command before execution prefixed with
>>>. - Prefer
-o jsonor--queryflags for parsable output. - Respect namespace: include
-n <namespace>when provided. - Do not prompt for confirmation; commands must run non-interactively.
- When a command fails, capture a concise error summary and continue.
Output Format
Return compact JSON on stdout:
[
{
"domain": "Pod Scheduling",
"findings": [
"Pod trainer-0 Pending: 0/3 nodes available: Insufficient nvidia.com/gpu"
],
"raw_snippets": [
"Warning FailedScheduling ... 0/3 nodes available: 3 Insufficient nvidia.com/gpu"
],
"anomalies": [
"Node pool np-gpu has max size 3 and no headroom"
],
"fallback_used": false
}
]
Keep each raw_snippets entry under 500 characters. If command output is huge, store only the most relevant fragment. Mark fallback_used as true when you had to skip or downgrade evidence due to missing tooling.
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.
- 6d ago First seen · 75 lines · 19 tokens per session scan A 9dbde973e2af
oke-evidence-collector is an agent published in the GitHub repository chiphwang1/oke-agent-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 19 tokens to every session and 693 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 2026-08-31.
Other agents, from other repositories
AWS Incident Triage
On-call SRE agent that drives structured CloudWatch-based incident investigation from alarms through root-cause hypothesis.
Cloud and SaaS Outage Triage
Distinguish upstream cloud or SaaS incidents from application failures before changing code, using live official-feed status and incident timelines.
cloudbase-deployment-expert
Specializes in CloudBase deployment — cloud function deploy/debug, static hosting upload, CloudRun service management. Use when troubleshooting deployments, checking build logs, or diagnosing runtime errors.
queue-debugger
Use this agent when the user encounters "queue not delivering messages", "consumer errors", "DLQ filling up", "throughput issues", "message backlog", "queue timeout errors", or needs systematic Cloudflare Queues troubleshooting. Examples.
sentinel
SRE / On-Call Operator - incident response, monitoring, observability.
sre
站点可靠性工程师,负责系统可用性保障、事故响应、容量规划、SLO/SLI定义和自动化运维.