meta-templates

meta-templates is a skill for Claude Code from martineserios/thebrana. It costs 40 tokens per session (1,670 once invoked), scanned A, original, MIT.

A command-line tool for managing WhatsApp message templates submitted to Meta, including their status, audits, snapshots, and appeals.

In plain words
What is it for?
It is for submitting templates from YAML files, checking templates in a WhatsApp Business Account, pulling baselines, auditing drift, and preparing appeals.
Why use it?
It helps teams track template changes and catch silent reclassifications, status changes, or quality drops. It also prepares appeal materials when Meta reclassifies a template.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the brana plugin — 56 skills, 4 commands, 14 agents, 13 hooks shipped together

Good fit It is for submitting templates from YAML files, checking templates in a WhatsApp Business Account, pulling baselines, auditing drift, and preparing appeals.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/martineserios/thebrana/meta-templates
Install

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.

Any agent
npx skills add martineserios/thebrana --skill meta-templates
Clone the repo
git clone --depth 1 https://github.com/martineserios/thebrana

Made for: Claude Code.

Or install brana, the plugin that ships this one along with the rest of its 56 skills, 4 commands, 14 agents, 13 hooks.

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.

agentmods badge for meta-templates

README.md
[![agentmods](https://agentmods.dev/badge/skills/martineserios/thebrana/meta-templates/github.svg)](https://agentmods.dev/skills/martineserios/thebrana/meta-templates)
Your own site
<a href="https://agentmods.dev/skills/martineserios/thebrana/meta-templates"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/meta-templates/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.

agentmods 80×15 button for meta-templates

Your own site · 80×15
<a href="https://agentmods.dev/skills/martineserios/thebrana/meta-templates"><img src="https://agentmods.dev/badge/skills/martineserios/thebrana/meta-templates.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,670 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.01670
Opus 5 $0.00020 $0.00835
Sonnet 5 $0.00008 $0.00334
Haiku 4.5 $0.00004 $0.00167

Measured 9d ago against content hash d51d162b51e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

meta-templates scanned grade A 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 9d 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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 600 ~/.config/brana/meta/<client>.env

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

system/skills/meta-templates/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Meta Templates — Programmatic Management

Wraps the local CLI brana-meta-templates (installed at ~/.local/bin/brana-meta-templates). Each subcommand passes through to the CLI with the client autodetected from the current working directory.

Source: ~/enter_thebrana/tools/brana-meta-templates/ ADR: clients/somos_mirada/decisions/2026-05-meta-template-tooling.md API reference: brana-knowledge/dimensions/54-meta-whatsapp-template-api.md

When to use

  • Submit a new WhatsApp template to Meta from a YAML definition
  • Check current status of one or all templates for a client's WABA
  • Pull a snapshot of all templates (baseline for drift detection)
  • Audit drift since last pull — detects silent reclassifications, status changes, quality drops
  • Prepare an appeal for a reclassified template (URLs + paste-ready copy)

Prerequisites — first-time setup per client

The CLI looks up auth at ~/.config/brana/meta/<client>.env. Onboarding a client requires creating that file once:

The env file must define two keys: META_SYSTEM_TOKEN (System User token from Meta Business Manager — Users → System Users → Generate Token, with permissions whatsapp_business_management, whatsapp_business_messaging, business_management) and META_WABA_ID (WhatsApp Account id, visible in the WhatsApp Account info panel of Business Manager).

Once you have both values, write the file:

mkdir -p ~/.config/brana/meta
$EDITOR ~/.config/brana/meta/<client>.env
chmod 600 ~/.config/brana/meta/<client>.env

If the file is missing, the CLI prints a config error pointing at the expected path.

Verify immediately after provisioning — run pull to confirm the WABA ID and token are correct before any submit attempt. A wrong WABA ID surfaces as a Graph API 400 on pull, not on submit, making diagnosis much faster:

brana-meta-templates pull --client <client>

If pull returns a 400 "does not exist or missing permissions", the WABA ID is wrong — correct META_WABA_ID in the env file. If it returns a 401, the token is invalid or lacks permissions.

Read the full file on GitHub · 146 lines

Changes

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.

  1. 9d ago First seen · 146 lines · 40 tokens per session scan A d51d162b51e9

Subscribe to this mod's changes

meta-templates is a skill published in the GitHub repository martineserios/thebrana (3 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,670 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

docs-audit

A scheduled review that looks for documentation that may no longer match recently changed source code. It examines Git history and searches documentation for references to changed files or names.

ChanningLua/prax-agent · 30 tokens

skill-navigator

A skill that recommends which already-installed local agent skill matches a described task. It uses the machine's skill catalogue and does not perform the task itself.

GrubbyLee/skill-manager · 83 tokens

gr-core

A routing guide for an international growth toolkit. It maps common questions—such as falling search rankings, launching on Product Hunt, or studying competitors—to the appropriate specialised guide.

Gingiris-1031/gingiris-skills · 77 tokens

absolute-audit

Vulnerability and security scan (defensive, your own repo): dependency CVEs plus risky code patterns (secrets, injection, weak authz), severity x reachability triaged and remediated without suppressing. Complements the built-in /security-review. Triggers on "absolute audit", "security audit", "are we vulnerable"…

maddhruv/absolute · 91 tokens

template-audit

Audit and quality-gate scripts for the template research framework. Covers documentation linting, filepath audits, mock-usage checking, template drift, and confidentiality / git-guard checks.

docxology/template · 40 tokens

skill-register-care

Pflege-Skill, der das dreiteilige Skill-Register konsistent hält (code-skill-index-Kataloge, Skill-Index, SKILL-MAP Family-/Routing-Map). Nutze diesen Skill für einen Drift-Check zwischen dem realen Skill-Inventar und dem dokumentierten Register: fehlende oder zu viele Einträge melden, Counts korrigieren, Stand-Datum…

ellmos-ai/skills · 117 tokens