agentmods.dev

adsagent-reliability

adsagent-reliability is a skill for Claude Code from adsagents/adsagent-ai-skills. It costs 33 tokens per session (346 once invoked), scanned A, original, MIT.

A reliability guide for AdsAgent MCP calls, which are requests to an AdsAgent service through a tool interface. It addresses failed, repeated, parallel, queued, partial, uncertain, and retryable results.

In plain words
What is it for?
Use it when AdsAgent requests fail, repeat, fan out, queue, or return partial, uncertain, or retryable evidence.
Why use it?
It helps distinguish a real failure from incomplete or uncertain evidence and prevents unreliable calls from being treated as confirmed results.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the adsagent plugin — 9 skills, 3 MCP servers shipped together

not rated 1repo changed yesterday A scan 33 tokens original MIT

Good fit Use it when AdsAgent requests fail, repeat, fan out, queue, or return partial, uncertain, or retryable evidence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adsagents/adsagent-ai-skills/adsagent-reliability
View source ↗ adsagents/adsagent-ai-skills adsagent.md
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 adsagents/adsagent-ai-skills --skill adsagent-reliability
Clone the repo
git clone --depth 1 https://github.com/adsagents/adsagent-ai-skills

Made for: Claude Code.

Or install adsagent, the plugin that ships this one along with the rest of its 9 skills, 3 MCP servers.

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 adsagent-reliability

README.md
[![agentmods](https://agentmods.dev/badge/skills/adsagents/adsagent-ai-skills/adsagent-reliability/github.svg)](https://agentmods.dev/skills/adsagents/adsagent-ai-skills/adsagent-reliability)
Your own site
<a href="https://agentmods.dev/skills/adsagents/adsagent-ai-skills/adsagent-reliability"><img src="https://agentmods.dev/badge/skills/adsagents/adsagent-ai-skills/adsagent-reliability/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 adsagent-reliability

Your own site · 80×15
<a href="https://agentmods.dev/skills/adsagents/adsagent-ai-skills/adsagent-reliability"><img src="https://agentmods.dev/badge/skills/adsagents/adsagent-ai-skills/adsagent-reliability.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 346 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00033 $0.00346
Opus 5 $0.00016 $0.00173
Sonnet 5 $0.00007 $0.00069
Haiku 4.5 $0.00003 $0.00035

Measured yesterday against content hash 3927f40f7db4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

adsagent-reliability 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 yesterday.

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.

skills/adsagent-reliability/SKILL.md · 30 lines

What it actually says

AdsAgent Reliability

  1. Classify the result as read retry, queued work, known-not-sent write, uncertain write, or operator review.
  2. Obey the returned next_action, task_ref, Retry-After, and capability gates. Wait for poll_after_ms before each task poll and stop at terminal; a local waiting deadline preserves the task reference, never resubmits it. Never infer a retry from prose alone.
  3. Retry only bounded reads or operations explicitly proven not sent. Never replay a confirm or parallelize recovery.
  4. Consume terminal results directly. Preserve completeness, receipts, continuation, and support_ref boundaries.
  5. For reconciled Meta create/copy, follow read-only create_reconciliation.next_action once; it verifies live state, not spend, and never authorizes replay.
  6. Stop on unclassified, permission, or operator-review outcomes.
  7. Legacy session recovery applies only after a negotiated legacy protocol; modern MCP 2026-07-28 is stateless.

Read recovery-contract.md and, when advertised, mutation-lifecycle-contract.md and plan-reconciliation-contract.md. Use retry-parser.md for transport backoff and meta-quota-plan.md only for strict Meta quota defer.

Files

What ships with it

5 files 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.

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. yesterday Changed · +2 lines 3927f40f7db4
  2. 10d ago First seen · 28 lines · 33 tokens per session scan A c336a59285e8

Subscribe to this mod's changes

adsagent-reliability is a skill published in the GitHub repository adsagents/adsagent-ai-skills (1 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 346 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 2026-08-31.

Debuggingadsagentagent-skillsgoogle-adsmcpmeta-adstiktok-ads
Related

Other skills, from other repositories

adspirer-ads-agent

Adspirer — AI-powered advertising and performance marketing agent. Manage Google Ads, Meta Ads (Facebook & Instagram), LinkedIn Ads, and TikTok Ads via natural language. 100+ tools for paid media campaign creation, live performance analysis, PPC keyword research with real CPC data, budget optimization, ad creative…

LeoYeAI/openclaw-master-skills · 141 tokens

adspirer-ads-agent

Adspirer — AI-powered advertising and performance marketing agent. Manage Google Ads, Meta Ads (Facebook & Instagram), LinkedIn Ads, and TikTok Ads via natural language. 400+ tools for paid media campaign creation, live performance analysis, PPC keyword research with real CPC data, budget optimization, ad creative…

amekala/ads-mcp · 187 tokens

ads

Use when running or fixing paid acquisition on Google or Meta — campaign structure (Performance Max, Demand Gen, Search, Advantage+), platform-fit creative, budget/scaling rules, break-even ROAS math, and Consent Mode v2 / CAPI tracking gaps. NOT the page the ad clicks into (that is landing-copy), NOT the channel-mix…

ericrisco/rsc-harness · 81 tokens

incident-postmortem

Close the learning loop after a rescue or incident — reconstruct the timeline from actionlog, run root-cause analysis (platform / site / measurement / external), produce a structured postmortem document, distill reusable insights via /learn, and propose preventive guardrails. Use after a /rescue, a CPA spike, a…

logly/mureo · 150 tokens

copy-de-anuncio

Cria copy de anúncios para Meta Ads, Google Ads e LinkedIn Ads com contexto do mercado brasileiro. Produz headline, texto principal, CTA e variações para teste A/B respeitando os limites de caracteres de cada plataforma.

ricneves-ai/flowgrammers-skills · 53 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens