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 martineserios/thebrana --skill meta-templatesgit clone --depth 1 https://github.com/martineserios/thebranaWrote 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/martineserios/thebrana/meta-templates)<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.
<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>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 | $0.00040 | $0.01670 |
| Opus 5 | $0.00020 | $0.00835 |
| Sonnet 5 | $0.00008 | $0.00334 |
| Haiku 4.5 | $0.00004 | $0.00167 |
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.
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.
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.
- 9d ago First seen · 146 lines · 40 tokens per session scan A d51d162b51e9
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.
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.
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.
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.
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"…
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.
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…