roasr-hermes

roasr-hermes is a skill for Claude Code, Codex from RoASr-com/roasr-mcp. It costs 128 tokens per session (2,162 once invoked), scanned A, original, MIT.

A skill for using RoASr in Hermes to audit Meta, Google Ads, and Yandex Direct accounts. Hermes is the agent environment, while RoASr is the connected advertising-analysis service.

In plain words
What is it for?
Use it to review account audits, find wasted budget, inspect search and moderation details, analyse competitor creatives, and pause or resume campaigns when authorised.
Why use it?
It helps identify costly advertising problems and inspect competitor ads without manually gathering the data from each platform.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to review account audits, find wasted budget, inspect search and moderation details, analyse competitor creatives, and pause or resume campaigns when authorised.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/roasr-com/roasr-mcp/hermes
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 RoASr-com/roasr-mcp --skill hermes
Clone the repo
git clone --depth 1 https://github.com/RoASr-com/roasr-mcp

Made for: Claude Code, Codex.

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 roasr-hermes

README.md
[![agentmods](https://agentmods.dev/badge/skills/roasr-com/roasr-mcp/hermes/github.svg)](https://agentmods.dev/skills/roasr-com/roasr-mcp/hermes)
Your own site
<a href="https://agentmods.dev/skills/roasr-com/roasr-mcp/hermes"><img src="https://agentmods.dev/badge/skills/roasr-com/roasr-mcp/hermes/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 roasr-hermes

Your own site · 80×15
<a href="https://agentmods.dev/skills/roasr-com/roasr-mcp/hermes"><img src="https://agentmods.dev/badge/skills/roasr-com/roasr-mcp/hermes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,162 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 $0.00128 $0.02162
Opus 5 $0.00064 $0.01081
Sonnet 5 $0.00026 $0.00432
Haiku 4.5 $0.00013 $0.00216

Measured 9d ago against content hash ca675e91adc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

roasr-hermes 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 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.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/hermes/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RoASr in Hermes — ad audit, competitor spy & Vision creative analysis

RoASr connects to a user's Meta, Google Ads and Yandex Direct data and returns an A–F account audit with findings ranked by money at stake, plus competitor intelligence from the Meta Ad Library and Vision analysis of creatives. This skill drives RoASr from Hermes through RoASr's remote MCP endpoint. Access is scoped to the user's own workspace; isolation and scopes are enforced API-side. Everything is read-only except one campaign pause/resume tool, which only works inside permissions the owner granted explicitly.

Setup (do this first — and tell the user if they haven't)

RoASr is a hosted service. Hermes cannot use it without the user's own account and API key.

  1. Sign up or log in at https://roasr.com — it's free.
  2. Go to Settings → API keys and create a key pg_live_… (owner/admin) with the scopes you need. The token is shown once — copy it.
  3. Add RoASr as a remote MCP connector in Hermes. In Hermes' MCP / connectors / integrations settings, add a new MCP server of type HTTP (remote / streamable):
    Name:  roasr
    URL:   https://roasr.com/api/mcp
    Auth:  Bearer pg_live_…        (Authorization header)
    
    No install is needed — Hermes talks to the hosted endpoint directly.
  4. Reload connectors and confirm the roasr_* tools appear.

If no API key is set, or a tool returns an auth error (auth.invalid_api_key / 401): tell the user to sign up free at https://roasr.com, open Settings → API keys, create a key, and paste it as the connector's Bearer token. Do not retry tools until a valid key is configured.

Tools (and required scope)

  • roasr_list_findings — AI audit findings ranked by priority (severity high/med/low); optional clientId. scope findings:read
  • roasr_metrics_summary — KPI summary (spend, impressions, clicks, conversions, revenue, CTR/CPC/CPM/ROAS/CPA, reach, frequency). Optional entityRef (campaign:<id> | adset:<id>) scopes to one entity. scope metrics:read
  • roasr_metrics_daily — daily time series of the same metrics, for trends/charts. Optional entityRef. scope metrics:read
  • roasr_metrics_breakdown — metrics segmented by dimension (audience/placement/platform/country/region/device/dma/hourly), required dimension, optional limit. scope metrics:read
  • roasr_metrics_campaigns — per-campaign/adset metrics and KPIs sorted by spend; optional level (campaign/adset), limit. scope metrics:read
  • roasr_metrics_actions — conversion breakdown by action type: actions (raw action-type → sum) + buckets (canonical: purchase, lead, add_to_cart, complete_registration, landing_page_view, engagement…; buckets aren't additive). scope metrics:read
  • roasr_list_clients — workspace clients with context (name, niche, margin, status). scope clients:read
  • roasr_spy_tag_leaderboard — competitor creative tag leaderboard; optional limit (1–100, default 20). days_live ≈ winning-ad proxy. scope spy:read
  • roasr_spy_search — search stored competitor creatives by query (keyword/hook/title/tag) and/or brand (page name); optional limit. Returns hook, title, format, tags, country and adArchiveId. scope spy:read
  • roasr_vision_analyze — Vision breakdown of one creative by adArchiveId (hook, angle, format, strengths, risks + video transcription). scope spy:read
  • roasr_signals — rich platform signals by required kind (16: Google/Meta search terms, keyword quality score, impression share, auction insights, conversion actions, asset performance, landing pages, shopping, video funnel, bidding, asset groups, Meta ad quality, plus the four Direct kinds). Optional limit. scope metrics:read
  • roasr_yandex_goals — which Yandex.Metrika goals the account's conversions are counted against. No date window — current config. Empty goals means the conversion numbers cannot be attributed and must not be presented as a clean CPA. scope metrics:read
  • roasr_yandex_search_queries — Direct search queries for a window (text, campaign/ad group, match type, impressions, clicks, spend, conversions). The most valuable Direct signal: use it to size the share of spend on queries with zero conversions. scope metrics:read
  • roasr_yandex_ads — Direct ads with moderation state and metrics: state/status/statusClarification, second headline, sitelinks, UTM markup, image, turbo page. Finds rejected and half-built ads. scope metrics:read
  • roasr_yandex_breakdown — one Direct call by dimension: search_queries | keywords | ads | bidding. scope metrics:read
  • roasr_limits — remaining daily Yandex API unit quota and plan limits. Direct meters per login and its Reports endpoint hides its own consumption, so check this before a heavy pull. scope metrics:read
  • roasr_campaign_set_statethe one write tool: pauses/resumes a live Direct campaign, only within permissions the owner granted for that key. Confirm with the human first; on a timeout retry with the same idempotencyKey, never a fresh one. scope campaigns:write
  • roasr_command_get — resolve a write command left in verifying/unknown by its id. scope campaigns:read

Read the full file on GitHub · 78 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 · 78 lines · 128 tokens per session scan A ca675e91adc9

Subscribe to this mod's changes

roasr-hermes is a skill published in the GitHub repository RoASr-com/roasr-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 128 tokens to every session and 2,162 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

google-ads-mcp

Unofficial Google Ads MCP. Dual MCP/CLI surface. Operator playbooks live in the separate google-ads skill suite — do not duplicate them here. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants Google Ads MCP data or actions through an agent.

davidmosiah/google-ads-mcp-unofficial · 64 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

unity-version-split

Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).

IvanMurzak/Unity-MCP · 59 tokens

specflow-use

To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.

griddynamics/rosetta · 27 tokens

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, then fills the gaps with list (filters, sort, a time…

comet-ml/opik-mcp · 174 tokens

ue-mcp-epic-routing

Use when deciding between ue-mcp's native category actions and Epic's wrapped ToolsetRegistry tools (the epic actions, incl. the Blueprint graph DSL) for a task in Unreal. Pulls in when authoring Blueprint graph bodies, or any time both a native action and an epic action could do the job and you need to pick.

db-lyon/ue-mcp · 81 tokens