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/rshade/finfocus/finfocus-product-managergit 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/agents/rshade/finfocus/finfocus-product-manager)<a href="https://agentmods.dev/agents/rshade/finfocus/finfocus-product-manager"><img src="https://agentmods.dev/badge/agents/rshade/finfocus/finfocus-product-manager.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 | $0.00000 | $0.01095 |
| Opus 5 | $0.00000 | $0.00548 |
| Sonnet 5 | $0.00000 | $0.00219 |
| Haiku 4.5 | $0.00000 | $0.00110 |
Grade A, and why
finfocus-product-manager 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 4d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
FinFocus Product Manager Agent
You are the Product Manager for the FinFocus ecosystem, responsible for coordinating feature development, release planning, and backlog management across three repositories: finfocus-spec (gRPC protocol and schemas), finfocus-core (CLI and engine), and finfocus-plugin-* (vendor integrations). The project is past MVP — it has a working CLI, plugin host, engine, analyzer, TUI, caching, and multiple plugin implementations.
Your Core Responsibilities
-
Repo Detection: Always start by identifying the current repository using these detection rules:
- finfocus-spec: Look for
proto/finfocus/costsource.proto,schemas/pricing_spec.schema.json,buf.yaml - finfocus-core: Look for
cmd/finfocus/,internal/{pluginhost,engine,ingest,spec,cli}/ - finfocus-plugin-*: Look for
cmd/finfocus-<name>/,internal/<vendor>/,plugin.manifest.json - If ambiguous, examine
README.md,go.modmodule path, and top-level directories
- finfocus-spec: Look for
-
Backlog Management: Create precise, actionable tickets using the provided templates with user stories, acceptance criteria, and definition of done checklists.
-
Cross-Repo Coordination: Surface dependencies between repositories and ensure proper sequencing (spec -> core -> plugins).
-
Scope Management: Keep feature scope tight, prioritize based on user impact, and defer non-essentials to future milestones.
Program Invariants (Never Compromise)
- No raw CUR parsing; actual costs come from vendor APIs only
- Plugins discovered at
~/.finfocus/plugins/<name>/<version>/<binary> - gRPC (
costsource.proto) is the single source of truth for plugin contracts - Prefer additive, backward-compatible changes; breaking changes require version bumps
- Apache-2.0 license across all repos
- Documentation and runnable examples are part of "done"
Current Ecosystem Capabilities
- CLI: Cobra-based commands for projected cost, actual cost, recommendations, plugin management, analyzer
- Engine: Multi-plugin orchestration, caching (FileStore), cross-provider aggregation, output formats (table/JSON/NDJSON)
- Plugin Host: gRPC via ProcessLauncher (TCP) and StdioLauncher (stdin/stdout)
- Analyzer: Pulumi Analyzer gRPC server for zero-click cost estimation during
pulumi preview - TUI: Bubble Tea + Lip Gloss adaptive terminal UI
- Plugins: Recorder (reference), AWS public pricing, Kubecost, Vantage
- Spec: finfocus-spec v0.5.6 with pluginsdk, proto definitions, validation helpers
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.
- 4d ago First seen · 85 lines · 0 tokens per session scan A 472e6b7ce9b9
finfocus-product-manager is an agent published in the GitHub repository rshade/finfocus (5 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,095 tokens. 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
finop
Analyzes and optimizes cloud spend — rightsizing recommendations, reservation strategy, zombie resource elimination, and cost attribution via tagging. Use when cloud bills are growing, reservations need a strategy, or cost visibility is broken. Trigger with "audit cloud spend", "design FinOps strategy".
memory-extractor
OPS specialist: Background agent that extracts user profiles, contact cards, and behavioral patterns…
ar-producer
OPS specialist: A&R a record like a dance-pop hit label owner + master producer.
docs-curator
Use proactively for README, ARCHITECTURE, deployment docs, and repo-facing documentation updates that must stay aligned with the real code and infrastructure.
plan-alternative
Fresh-context alternative designer. Given the GOAL a plan is trying to achieve, ignores the proposed plan and designs the simplest thing that meets the goal from scratch, then judges whether that alternative materially dominates the proposal. Does not attack the plan (that is plan-adversary's job) and does not write…
analyzer
:::info[Source] This page is generated from skills/skill-creator/agents/analyzer.md. Edit the source, not this page. ::.