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 rshade/finfocus --skill finfocus-diagnosegit clone --depth 1 https://github.com/rshade/finfocusWrote 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/rshade/finfocus/finfocus-diagnose)<a href="https://agentmods.dev/skills/rshade/finfocus/finfocus-diagnose"><img src="https://agentmods.dev/badge/skills/rshade/finfocus/finfocus-diagnose/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/rshade/finfocus/finfocus-diagnose"><img src="https://agentmods.dev/badge/skills/rshade/finfocus/finfocus-diagnose.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00119 | $0.00723 |
| Opus 5.5 | $0.00048 | $0.00289 |
| Sonnet 5.5 | $0.00024 | $0.00145 |
| Haiku 4.5 | $0.00012 | $0.00072 |
Grade A, and why
finfocus-diagnose 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 13d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnose FinFocus
This skill is FinFocus-specific. Read the reference that matches the symptom before changing config or deleting cache files.
Install: npx skills add rshade/finfocus -s finfocus-diagnose.
1. Name the symptom
| What you see | Open |
|---|---|
connection refused, broken pipe, EOF, no such file or directory, bind timeout |
Plugin connectivity |
| The wrong plugins load, or an edit has no effect | Config resolution |
Stale prices, (cached) on the adapter, or a locked cache.db |
Cache |
Every resource is $0, or a note starts with VALIDATION: or ERROR: |
Zero cost |
PLUGIN_ERROR, VALIDATION_ERROR, TIMEOUT_ERROR, NO_COST_DATA |
Error codes |
Commands, flags, and environment variables: references/diagnostic-commands.md.
2. Collect evidence before changing anything
finfocus plugin list --verbose
finfocus plugin validate
finfocus config routes list
finfocus config list
finfocus cost projected --debug --pulumi-json plan.json
finfocus config routes test <resource-type> [region] simulates selection.
It does not launch plugin binaries.
Log level precedence is --debug, then FINFOCUS_LOG_LEVEL, then the config file, then info.
The default format value is text. FINFOCUS_LOG_FORMAT=json switches to JSON.
FINFOCUS_TRACE_ID overrides the generated trace id. gRPC metadata uses x-finfocus-trace-id.
3. Apply the matching fix
- Connectivity: confirm the binary, the executable bit, and
plugin.manifest.json, then retry. Core sets--portandFINFOCUS_PLUGIN_PORT. It does not setPORT. - Config: edit
config.hujson. A project file replaces a whole top-level key of the global file. - Cache:
FINFOCUS_CACHE_ENABLED=falseskips the cache. Deletingcache.dbdrops stored prices. Corruption is recreated on open. - Zero cost: read the note and the structured code before treating
$0as a failure. A returned monthly cost of 0 does not fall back to the next plugin.
What ships with it
4 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.
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.
- 13d ago First seen · 60 lines · 119 tokens per session scan A c254b459b5b2
finfocus-diagnose is a skill published in the GitHub repository rshade/finfocus (10 stars, last pushed today), licensed Apache-2.0. It adds 119 tokens to every session and 723 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-03.
Other skills, from other repositories
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.
postgresql-indexing
PostgreSQL indexing best practices for Prowler: index design, partial indexes, partitioned table indexing, EXPLAIN ANALYZE validation, concurrent operations, monitoring, and maintenance. Trigger: When creating or modifying PostgreSQL indexes, analyzing query performance with EXPLAIN, debugging slow queries, reviewing…
gh-aw
Create and maintain GitHub Agentic Workflows (gh-aw) for Prowler. Trigger: When creating agentic workflows, modifying gh-aw frontmatter, configuring safe-outputs, setting up MCP servers in workflows, importing Copilot Custom Agents, or debugging gh-aw compilation.
tdd
Test-Driven Development workflow for ALL Prowler components (UI, SDK, API). Trigger: ALWAYS when implementing features, fixing bugs, or refactoring - regardless of component. This is a MANDATORY workflow, not optional.
hyperpod-node-debugger
Diagnose and remediate per-node issues on a HyperPod cluster (EKS or Slurm) — a specific node is unhealthy, unresponsive, stuck, or needs replacing. Covers on-node EFA, GPU / accelerator hardware (XID, ECC, NVLink, row-remap, DCGM), Slurm node down/drained, disk and memory pressure, per-node lifecycle-script failures…
hyperpod-cluster-debugger
Diagnose and remediate cluster-wide HyperPod (EKS or Slurm) problems — creation / deployment failures (CloudFormation, EFA health check, lifecycle scripts, capacity), EKS access, node replacement, CloudFormation nested-stack errors, post-maintenance rollback state, dangling nodes, autoscaler conflicts. Includes…