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/tkilome/skillbound-agent/flink-intelligent-ops)<a href="https://agentmods.dev/skills/tkilome/skillbound-agent/flink-intelligent-ops"><img src="https://agentmods.dev/badge/skills/tkilome/skillbound-agent/flink-intelligent-ops.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 | $0.00045 | $0.06832 |
| Opus 5 | $0.00023 | $0.03416 |
| Sonnet 5 | $0.00009 | $0.01366 |
| Haiku 4.5 | $0.00005 | $0.00683 |
Grade C, and why
flink-intelligent-ops scanned grade C with 1 finding 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
`~/.kube/config`. The agent must not read or ask the user to paste kubeconfig How it starts
The opening of the file, as written. The whole thing — 506 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flink Intelligent Ops
Give a host agent shared Apache Flink intelligent operations capability.
MANDATORY EXECUTION RULE: When this skill is triggered, use only this skill's bundled Java CLI:
com.skill.flinkops.FlinkOpsCli
Never use kubectl, flink run-application, Flink shell scripts, hand-written
Kubernetes manifests, Flink Operator CRDs, cloud CLIs, or ad hoc scripts as
substitutes for skill execution. This rule applies to discovery, preflight,
submission, verification, logs, status, and troubleshooting. If the bundled CLI
cannot answer or perform an action, report the missing capability instead of
switching tools.
The key boundary is:
- Common operations use Flink REST and work for Kubernetes, YARN, standalone, or any deployment target that exposes a JobManager REST URL.
- Deployment operations are provider-specific. The MVP implements
--deployment-target kuberneteswith Flink native Kubernetes application mode.
Resolve Runtime Paths
Before running any command, resolve SKILL_DIR as the directory that contains
this SKILL.md. Do not assume the current working directory is the skill
directory.
Examples:
- Codex global install:
$HOME/.codex/skills/flink-intelligent-ops - Claude Code global install:
$HOME/.claude/skills/flink-intelligent-ops - Project-local example:
<repo>/example-skills/flink-intelligent-ops
Resolve runtime dependencies from the user's input, environment, or the selected deployment provider reference. Do not assume a provider-specific runtime rule applies to every deployment target.
The host platform or user must provide JAVA_HOME before any bundled CLI
command is executed. Use $JAVA_HOME/bin/java to launch this skill. Do not
fall back to java from PATH when JAVA_HOME is available or required by the
session.
JAVA_HOME collection is the first runtime gate. Before asking for Flink,
Kubernetes, YARN, REST, jar, image, or mutation-confirmation parameters, check
whether the current session already has a resolved JAVA_HOME. If not, ask
only for JAVA_HOME and stop. Do not run check_cli_environment, preflight,
read, diagnosis, build, start, or stop commands until JAVA_HOME is known.
Explain that this path is used to start the bundled Java CLI. Example:
/Users/example/Library/Java/JavaVirtualMachines/ms-11.0.28/Contents/Home.
What ships with it
60 files 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.
- assets/env.example 156 B
- assets/kubernetes/ingress-controller.yaml.tpl 3.6 KB
- evals/provider_cases.jsonc 1.2 KB
- evals/safety_cases.jsonc 574 B
- evals/schema_cases.jsonc 844 B
- evals/should_not_trigger.jsonc 779 B
- evals/should_trigger.jsonc 782 B
- evals/workflow_cases.jsonc 2.6 KB
- references/agent-operating-protocol.md 8.3 KB
- references/command-catalog.md 4.3 KB
- references/command-map.md 6.0 KB
- references/error-handling.md 2.3 KB
- references/playbooks/build-image.md 560 B
- references/playbooks/checkpoint-timeout.md 344 B
- references/playbooks/diagnose-job.md 579 B
- references/playbooks/start-job.md 1.7 KB
- references/playbooks/stop-job.md 636 B
- references/product-model.md 1.5 KB
- references/providers/kubernetes.md 16 KB
- references/providers/yarn.md 1.7 KB
- references/resource-disclosure.md 565 B
- references/safety-rules.md 2.4 KB
- references/verification-method.md 937 B
- schemas/build_image.schema.json 734 B
- schemas/check_cli_environment.schema.json 368 B
- schemas/check_ingress_controller.schema.json 488 B
- schemas/diagnose_backpressure.schema.json 665 B
- schemas/diagnose_job.schema.json 600 B
- schemas/get_checkpoints.schema.json 482 B
- schemas/get_exceptions.schema.json 481 B
- schemas/get_job_status.schema.json 456 B
- schemas/get_node_ips.schema.json 398 B
- schemas/inspect_cluster.schema.json 763 B
- schemas/k8s_build_image.schema.json 513 B
- schemas/k8s_check_connectivity.schema.json 469 B
- schemas/k8s_check_ingress_controller.schema.json 299 B
- schemas/k8s_get_node_ips.schema.json 205 B
- schemas/k8s_preflight_start.schema.json 532 B
- schemas/k8s_render_ingress_controller_yaml.schema.json 356 B
- schemas/k8s_start_job.schema.json 1.7 KB
- schemas/preflight_start.schema.json 932 B
- schemas/render_ingress_controller_yaml.schema.json 551 B
- schemas/start_job.schema.json 3.1 KB
- schemas/stop_job.schema.json 1.2 KB
- schemas/yarn_check_connectivity.schema.json 441 B
- scripts/pom.xml 2.4 KB
- scripts/src/main/java/com/skill/flinkops/cli/CommandHandler.java 179 B
- scripts/src/main/java/com/skill/flinkops/cli/CommandNames.java 2.1 KB
- scripts/src/main/java/com/skill/flinkops/cli/CommandRouter.java 948 B
- scripts/src/main/java/com/skill/flinkops/common/ApiResponse.java 3.3 KB
- scripts/src/main/java/com/skill/flinkops/common/CommandContext.java 2.6 KB
- scripts/src/main/java/com/skill/flinkops/common/errors/OperationException.java 1.1 KB
- scripts/src/main/java/com/skill/flinkops/common/errors/SafetyException.java 182 B
- scripts/src/main/java/com/skill/flinkops/common/errors/ValidationException.java 190 B
- scripts/src/main/java/com/skill/flinkops/common/Json.java 3.0 KB
- scripts/src/main/java/com/skill/flinkops/common/SafetyGate.java 367 B
- scripts/src/main/java/com/skill/flinkops/flink/compat/FlinkCompatibility.java 778 B
- scripts/src/main/java/com/skill/flinkops/flink/compat/FlinkCompatibilityRegistry.java 809 B
- scripts/src/main/java/com/skill/flinkops/flink/compat/FlinkVersion.java 879 B
- scripts/src/main/java/com/skill/flinkops/flink/compat/rest/DefaultRestDialect.java 631 B
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 · 506 lines · 45 tokens per session scan C f024f9e9cba9
flink-intelligent-ops is a skill published in the GitHub repository TKilome/skillbound-agent (2 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 45 tokens to every session and 6,832 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…