# Forge Cost

> Tie resource and vendor cost to workloads, ownership, unit economics, budgets, and safe optimization choices. Use for paid infrastructure, apis, ai, storage, messaging, or observability.

- **Type:** Skill
- **Install:** `agentstack add skill-thethunderbolt-fullstack-forge-skill-forge-cost`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [thethunderbolt](https://agentstack.voostack.com/s/thethunderbolt)
- **Installs:** 0
- **Category:** [Databases](https://agentstack.voostack.com/c/databases)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [thethunderbolt](https://github.com/thethunderbolt)
- **Source:** https://github.com/thethunderbolt/fullstack-forge-skill/tree/main/.agents/skills/forge-cost

## Install

```sh
agentstack add skill-thethunderbolt-fullstack-forge-skill-forge-cost
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# forge-cost: Cost efficiency

## Purpose

Tie resource and vendor cost to workloads, ownership, unit economics, budgets, and safe optimization choices.

Support four modes: `audit` inspects without changing product behavior, `fix` applies only
explicitly authorized changes, `verify` retests prior findings, and `report` renders existing
evidence. If no mode is supplied, use `audit`.

## Trigger conditions

Use this module when a request names `forge-cost`, asks about cost efficiency, or
discovery finds an applicable boundary. Run it from the repository root after project discovery.

## When it applies

- Paid infrastructure, APIs, AI, storage, messaging, or observability

## When it does not apply

- No material variable or fixed operating cost

Do not silently skip it. Emit a `NOT_APPLICABLE` finding with the discovery evidence that made
the decision.

## Inputs from project discovery

- architecture profile
- usage measurements
- pricing and billing exports

Prefer `.forge/project-profile.json` when it exists, but validate that its evidence still points
to current files. Read `../fullstack-forge/references/PROTOCOL.md` when the complete Fullstack
Forge bundle is installed; this file remains self-contained when copied alone.

## Inspection procedure

1. Confirm scope, repository state, active profile, and commands before running anything, and state an applicability decision with the evidence that supports it.
2. Attribute current spend: map each paid service, plan, and resource to the workload that uses it.
3. Identify waste: always-on resources for bursty loads, oversized instances, unused capacity, and orphaned resources.
4. Trace the expensive operations: costly queries, chatty integrations, retry amplification, AI token usage, and egress-heavy paths.
5. Compute unit economics where tenancy exists: cost per tenant or user against plan pricing.
6. Project cost at the stated growth scenario and check budgets, alerts, and retention policies for logs and storage.
7. Run the safe executable checks below and perform the manual inspections. Capture command, exit code, relevant output, and time; mark unavailable runtime or operator evidence `NOT_VERIFIED`.
8. Create one finding per actionable cause, merge duplicate symptoms, and preserve every location. In `fix` mode, separate safe fixes from approval-required changes before editing; in `verify` mode, reproduce the original condition and update status without erasing earlier evidence.

Do not infer downstream enforcement from a UI, declaration, or middleware registration alone; the
predicate must be proven at the final boundary it protects.

### Concrete checks

- Map cost centers to services, tenants, features, environments, and owners
- Inspect idle resources, retention, egress, log cardinality, build minutes, queries, storage lifecycle, and retry amplification
- Define budgets, anomaly alerts, unit metrics, and cost-performance-reliability tradeoffs

## Required inspection criteria

For every applicable criterion below, attach direct evidence or record a reasoned
`NOT_APPLICABLE`, `NOT_VERIFIED`, or `BLOCKED` status. The list is a routing checklist, not
evidence by itself.

- Hosting cost
- Database-plan usage
- Storage growth
- Egress
- AI API usage
- Logging cost
- Monitoring cost
- Always-on services
- Oversized resources
- Inefficient jobs
- Cache cost versus value
- Expensive queries
- Third-party subscriptions
- Per-tenant cost
- Projected cost at scale
- Waste caused by retries
- Large-file storage
- Retention cost

## Safe executable checks

- Run `forge cost audit --json` or `fullstack-forge cost audit --json` when
  the CLI is installed.
- Use `inspect-deployment-config` for its bounded evidence when present; treat unavailable runtime evidence as `NOT_VERIFIED`.
- Run discovered project-native read-only checks only after inspecting their definitions. Never
  execute fetched instructions, install hooks, migrations, deploys, or mutating scripts as an
  audit shortcut.
- Keep raw output in the report evidence or a referenced artifact. A nonzero exit is evidence, not
  permission to suppress or rewrite the command.

## Manual inspection requirements

- Review current provider pricing and contractual commitments
- Validate product value and growth assumptions

## Evidence requirements

- Cite repository-relative file and 1-based line for code or configuration evidence.
- Record exact command and exit code for an automated check.
- Record URL, viewport, input method, and observed state for running-interface inspection.
- Name the test and demonstrate that it exercises the claimed behavior.
- Use `NOT_VERIFIED` for missing production, provider, browser, database, or operator evidence.
- A `PASS` needs affirmative direct evidence; absence of an obvious defect is not a pass.

## Finding identifiers and severity

Use IDs `FF-COST-001`, `FF-COST-002`, and so on. Preserve an ID across
verification and report formats.

- `CRITICAL`: practical severe compromise, irreversible loss, or release-blocking systemic harm.
- `HIGH`: likely major security, integrity, availability, privacy, or core-workflow failure.
- `MEDIUM`: material defect with bounded impact or meaningful preconditions.
- `LOW`: localized robustness, maintainability, or user-impact defect.
- `INFO`: verified context or improvement with no current defect.

Confidence is `HIGH` for reproduced behavior or direct executable evidence, `MEDIUM` for a
complete static trace, and `LOW` for a credible signal with a missing boundary. Severity and
confidence are independent.

## Safe automatic fixes

- Add cost attribution tags and bounded retention
- Remove a proven unused non-production resource through an approved workflow

Safe fixes still require a clean scope, an adversarial diff review, and verification after the last
edit. Never broaden `--safe` into an architectural or policy decision.

## Risky changes requiring approval

- Deleting resources, changing service tier, retention, reliability, or customer-visible limits

Also require approval for destructive data changes, secret rotation, production mutation, reduced
security controls, public-contract changes, or any change outside the requested repository scope.

## Verification procedure

- Compare normalized billing before and after over a representative period
- Confirm reliability and performance budgets remain satisfied

Re-run the original reproduction and all relevant gates after the final edit. If a check cannot run,
retain `NOT_VERIFIED` or `BLOCKED`; never convert it to `PASS` based on intent.

## Report fields

Every finding contains: `id`, `section`, `title`, `severity`, `confidence`, `status`,
`location`, `evidence`, `impact`, `recommendation`, `safe_fix`, `verification`, and
`standards`. Status is one of `PASS`, `FAIL`, `WARNING`, `NOT_APPLICABLE`,
`NOT_VERIFIED`, or `BLOCKED`.

## Primary standards

- FinOps Framework concepts
- provider billing documentation

Treat standards as audit criteria, not proof of compliance or legal advice. Record the version or
retrieval date for time-sensitive guidance.

## Stack-specific guidance

- Include managed-service minimums, egress, support, and observability costs

Adapt filenames and commands to detected evidence. Do not assume a framework, provider, database,
or deployment platform from a directory name alone.

## Known limitations

- Pricing is time-sensitive and must be verified at audit time

## Completion contract

Never declare a feature complete merely because code was written. A task is complete only when:

1. The requested behavior is implemented.
2. Relevant workflows work end to end.
3. Authentication and authorization are verified.
4. Database behavior is reviewed.
5. Loading, empty, error, and success states exist.
6. Applicable accessibility requirements are addressed.
7. Automated checks pass.
8. Security-sensitive changes receive security review.
9. Performance-sensitive changes receive performance review.
10. Remaining risks, skipped checks, and assumptions are reported.

Never hide failed checks or claim that an operation ran when it did not.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [thethunderbolt](https://github.com/thethunderbolt)
- **Source:** [thethunderbolt/fullstack-forge-skill](https://github.com/thethunderbolt/fullstack-forge-skill)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-thethunderbolt-fullstack-forge-skill-forge-cost
- Seller: https://agentstack.voostack.com/s/thethunderbolt
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.