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 skills/fmind/dot/firebasenpx skills add fmind/dot --skill firebasegit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/firebase)<a href="https://agentmods.dev/skills/fmind/dot/firebase"><img src="https://agentmods.dev/badge/skills/fmind/dot/firebase.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 | $0.00037 | $0.01055 |
| Opus 5 | $0.00018 | $0.00528 |
| Sonnet 5 | $0.00007 | $0.00211 |
| Haiku 4.5 | $0.00004 | $0.00105 |
Grade A, and why
firebase 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 today.
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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Firebase Standard
Firebase is the default backend and hosting for TypeScript web apps: Auth, Firestore, Cloud Functions, Hosting for static bundles, App Hosting for SSR. The firebase CLI comes from mise; the upstream skills carry the product detail, so this skill fixes the workflow, the local loop, and the deploy authority.
1. Setup
- Authenticate once:
firebase login(orfirebase login --no-localhoston a headless machine);firebase projects:create <project-id>orfirebase use <project-id>in the repo. - Initialize features:
firebase init <feature>forfirestore,hosting,functions, orapphosting; answers land infirebase.json,.firebaserc,firestore.rules, andfirestore.indexes.json, all committed. - Angular integration:
ng add @angular/firein the app per angular; keep the Firebase config insrc/environments/and never commit service-account keys.
2. Local Loop
firebase emulators:start # Auth, Firestore, Functions, Hosting on localhost with the Emulator UI
firebase emulators:exec "mise run test" # run the suite against emulators, then stop them
- Point the app at the emulators in development (
connectAuthEmulator,connectFirestoreEmulator) behind an environment flag, never in production builds. - Rules are tested with
@firebase/rules-unit-testingagainst the emulator; run them frommise run testso hooks and CI cover them.
3. Deploy
firebase deploy --only firestore:rules,firestore:indexes # rules first, reviewed as code
firebase deploy --only hosting # static bundle from mise run build
firebase hosting:channel:deploy preview-<branch> --expires 7d # preview URL for review
firebase deploy --only functions # Cloud Functions (2nd gen, Node LTS)
firebase deploy --only apphosting # SSR backends (Blaze plan)
- Expose deployment as an explicit
deploymise task per mise; it never runs from a hook because it mutates production and can cost money. - CI deploys authenticate with Workload Identity Federation (
google-github-actions/auth) andfirebase deploy --project <id>; noFIREBASE_TOKENsecrets — see github-actions. - Audit the rules with the upstream security-rules skill before every rules deploy; its score and findings go in the PR.
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.
- today Changed e6610732b6e2
- yesterday First seen · 67 lines · 37 tokens per session scan A 8fdf46b14552
firebase is a skill published in the GitHub repository fmind/dot (4 stars, last pushed today), licensed MIT. It adds 37 tokens to every session and 1,055 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
cloud-run
Deploy container services to Google Cloud Run with Artifact Registry, keyless CI identity, Secret Manager, ko, or Dockerfiles.
google-cloud-operations
Operate Google Cloud with gcloud: pin account, configuration, project, and billing context for IAM, APIs, logs, and audits outside deployment.
terraform-stack
Canonical infrastructure-as-code stack — OpenTofu-first with tflint, trivy config scans, terraform-docs, native tests, and GCS state. Use for any Terraform or OpenTofu work.
go-stack
Build Go projects, libraries, CLIs, TUIs, web apps, or ADK agents with the standard package layout and pinned tooling.
python-stack
Build typed Python projects with uv, Ruff, ty, pytest, Litestar, and Typer. Use for packages, CLIs, web apps, tests, typing, or API verification.
k8s-local
Create and manage local Kubernetes clusters (k3d or kind) and deploy to them with kubectl, helm, helmfile, and skaffold. Use for local k8s cluster setup, dev loops, and debugging.