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 adbertram/cli-tools --skill facebook-ads-cligit clone --depth 1 https://github.com/adbertram/cli-toolsWrote 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/adbertram/cli-tools/facebook-ads-cli)<a href="https://agentmods.dev/skills/adbertram/cli-tools/facebook-ads-cli"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/facebook-ads-cli/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/adbertram/cli-tools/facebook-ads-cli"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/facebook-ads-cli.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 | $0.00082 | $0.00879 |
| Opus 5.5 | $0.00033 | $0.00352 |
| Sonnet 5.5 | $0.00016 | $0.00176 |
| Haiku 4.5 | $0.00008 | $0.00088 |
Grade A, and why
facebook-ads-cli 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.
What it actually says
<project_overrides> Before acting, run:
~/.agents/skills/skill-expert/scripts/load-skill-overrides.sh facebook-ads-cli
Apply printed instructions. No output means no override; nonzero means stop and report the broken override rather than silently proceeding. </project_overrides>
<quick_start>
Read adjacent usage.json for the wrapper contract. Read native command help
through facebook-ads run -- ... --help before service calls. Never copy the
retired custom SDK/Graph syntax or invent upstream options.
facebook-ads --help
facebook-ads --version
facebook-ads run -- --version
facebook-ads run -- --help
facebook-ads run -- ads --help
facebook-ads run -- ads campaign list --help
facebook-ads run -- ads creative create --help
facebook-ads run -- auth status
</quick_start>
<essential_principles>
- Official dependency is meta-ads==1.2.0, published by Meta on PyPI, executable meta. Canonical wrapper installation provisions it privately. Runtime uses that exact executable rather than an unrelated PATH command.
- Invoke every native operation as
facebook-ads run -- <native arguments>. Root help/version belong to the wrapper; help/version after the separator belong to Meta. The separator protects future/native flags from wrapper parsing. - Every native command and option passes through without a whitelist. Release 1.2.0 has 55 native leaf commands; this is upstream CLI coverage, not universal Graph API coverage. Native help remains authoritative.
- Upstream owns authentication. It reads ACCESS_TOKEN and account selection via AD_ACCOUNT_ID or native --ad-account-id; BUSINESS_ID/--business-id is optional. Upstream has auth status only: no auth login, OAuth/browser flow or wrapper authentication profiles. Status reports configured-token readiness, not live proof of account permissions.
- Use the owning CLI-tools secret-manager skill for reusable tokens. Inject its retrieved value into ACCESS_TOKEN for the command without printing it or storing it in raw .env files, docs, shell arguments or logs. Existing wrapper profiles/secret values are preserved but are not read or rewritten.
- Native global output is --output table|json|plain (-o), with table as native
default. JSON example:
facebook-ads run -- --output json ads adaccount list. Preserve native output and exit status; do not normalize or truncate data. - Native flags must be in the positions documented by upstream help. Do not invent retired --dry-run/--yes/--profile/filter/property options. Native --no-input suppresses prompts. Advertising mutations require user authorization; never launch ads or spend as a test.
- Wrapper inherits stdin/TTY, stdout, stderr and signals and executes without a shell. It never launches browser login or obtains credentials automatically. </essential_principles>
<reference_index>
usage.json: wrapper help/version and run passthrough contract.- Official Ads CLI overview
- Official Meta package </reference_index>
<success_criteria> Use native help to select exact command syntax, inject required environment credentials safely, preserve upstream output/errors, and verify the requested service outcome without claiming untested account permissions or API coverage. </success_criteria>
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 84 lines · 82 tokens per session scan A 5f096f915bc3
facebook-ads-cli is a skill published in the GitHub repository adbertram/cli-tools (6 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 879 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-07.
facebook-ads-cli compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| facebook-ads-cliadbertram/cli-tools | Skill | 6 | today | MIT | A | 82 | Claude Code, Codex |
| opencli-autofixjackwener/OpenCLI | Skill | 31k | yesterday | Apache-2.0 | A | 61 | Claude Code |
| surfnicobailon/surf-cli | Skill | 684 | yesterday | MIT | A | 53 | Claude Code, Codex |
| rdc-cliBANANASJIM/rdc-cli | Skill | 193 | 14d ago | MIT | A | 82 | Claude Code, Codex |
| pixiv-cli-ciFlanChanXwO/pixiv-cli | Skill | 132 | yesterday | MIT | A | 61 | Codex |
| acrawl-mcpMingye-Lu/AgenticCrawler | Skill | 15 | yesterday | MIT | A | 200 | Claude Code, Codex |
| debug-hubrexleimo/aios | Skill | 62 | yesterday | MIT | B | 66 | Claude Code, Codex |