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 kelpi-ai/meta-ads-skills --skill daily-auditorgit clone --depth 1 https://github.com/kelpi-ai/meta-ads-skillsWrote 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/kelpi-ai/meta-ads-skills/daily-auditor)<a href="https://agentmods.dev/skills/kelpi-ai/meta-ads-skills/daily-auditor"><img src="https://agentmods.dev/badge/skills/kelpi-ai/meta-ads-skills/daily-auditor/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/kelpi-ai/meta-ads-skills/daily-auditor"><img src="https://agentmods.dev/badge/skills/kelpi-ai/meta-ads-skills/daily-auditor.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 | $0.00062 | $0.00582 |
| Opus 5.5 | $0.00025 | $0.00233 |
| Sonnet 5.5 | $0.00012 | $0.00116 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
daily-auditor 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 2mo 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.
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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Daily Auditor
Doctrine
Nobody looks at your ad account every day. Not the agency (check the activity history), not Meta (its recommendations optimize Meta's revenue), usually not even you. Meanwhile the best community advice is "stop touching your campaigns", which only works if something is still watching. The resolution: read daily, act rarely. A read-only audit is what lets you keep your hands off without flying blind.
When to use
- Every morning, same time, whether things feel fine or not. Quiet failures are the expensive ones.
- Also: on any account managed by someone else, as an accountability check.
- Needs a Meta Ads MCP, read access only.
Run it
Run a READ-ONLY audit of my ad account. Change nothing. Compare the last 7 complete days against the prior 7, at campaign, ad set, and ad level, and give me at most 5 findings, ranked by dollars at stake:
1. Wasted budget: spend with zero results, and where it is pooling.
2. Fading ads: flag ONLY if frequency > 4.0 AND CTR is down 30%+ vs the prior window. Name the ad.
3. Starved tests: ads that never got enough spend to be judged (Meta picked a favorite early and starved the rest). Tell me which ads never got a real test.
4. Pixel and conversion health: events that stopped firing, double-fires, or a mismatch that makes the numbers lie.
5. The one next test worth running, based on what the winners share.
For every finding: the numbers behind it, from the account. If a number is not in the account, say "no data", never estimate. If nothing is wrong in a category, say so in one line. End with: "No changes were made."
Guardrails
- Read-only is the identity of this skill. It proposes; a human disposes.
- Max 5 findings. A 50-row dashboard dump is not an audit, it is homework.
- Week-over-week complete days only: partial days and lifetime views both lie.
- The fatigue rule (frequency > 4.0 AND CTR -30%) is a deliberate two-condition heuristic to avoid false alarms. It is falsifiable; if your data disagrees, tighten or loosen it and write down why.
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.
- 2mo ago First seen · 38 lines · 62 tokens per session scan A 7cb77395b4c8
daily-auditor is a skill published in the GitHub repository kelpi-ai/meta-ads-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 582 once invoked, about $0.0002 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 2026-08-31.
daily-auditor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| daily-auditorkelpi-ai/meta-ads-skills | Skill | 5 | 4mo ago | MIT | A | 62 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |