Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/logly/mureonpx agentmods add skills/logly/mureo/budget-rebalanceWrote 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/logly/mureo/budget-rebalance)<a href="https://agentmods.dev/skills/logly/mureo/budget-rebalance"><img src="https://agentmods.dev/badge/skills/logly/mureo/budget-rebalance/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/logly/mureo/budget-rebalance"><img src="https://agentmods.dev/badge/skills/logly/mureo/budget-rebalance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 65 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium Rogue Agent · line 10 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00106 | $0.01877 |
| Opus 5 | $0.00053 | $0.00938 |
| Sonnet 5 | $0.00021 | $0.00375 |
| Haiku 4.5 | $0.00011 | $0.00188 |
Grade A, and why
budget-rebalance 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 5d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Budget Rebalance
PREREQUISITE: Read
../_mureo-shared/SKILL.mdfor auth, security rules, output format, and Tool Selection (Read/Write on Code,mureo_strategy_*/mureo_state_*MCP on Desktop / Cowork).
Analyze budget allocation and suggest rebalancing across all campaigns.
Prerequisites
- STRATEGY.md and STATE.json must exist (run the
onboardskill first)
Steps
Before you start: Run the Diagnostic preamble from ../_mureo-shared/SKILL.md — load learning insights (mureo_learning_insights_get) and consult advisors (mureo_consult_advisor) before drawing conclusions.
-
Establish today: call
mureo_state_getfirst, on every host (including Claude Code, where you would otherwiseReadthe file) and takeserver_nowfrom its response — ISO 8601 with UTC offset, e.g.2026-07-28T10:12:33+09:00. Its date is the only source of the current date for this run: theobservation_dueyou write in step 16, and every "is a previous change still inside its observation window?" check in step 14, are measured from it. Do not shell out (this skill must run in Bash-less headless hosts) and do not read the date off STATE.json —last_synced_at,reports.*.periodandaction_logtimestamps are history, never evidence of what day it is now. Never writeserver_nowinto STATE.json: it is a response field, and a persisted copy becomes tomorrow's stale "today". -
Load context: Read STRATEGY.md (Operation Mode, Market Context, Goal sections, Data Sources) and STATE.json (the same
mureo_state_getresponse from step 0 on MCP hosts). -
Discover platforms: Identify all configured ad platforms from STATE.json
platforms. Also include any hosted official-MCP connector present in the session (e.g. TikTok, keytiktok_ads) — drive it via its own tools and skip mureo-only value-adds; see../_mureo-shared/SKILL.md→ Hosted-connector platforms. -
Analyze budget efficiency: For each ad platform:
- Google Ads: prefer mureo native — call
google_ads_budget_efficiency(campaign × budget × spend × conv ratio) andgoogle_ads_performance_reportfor the period. In BYOD mode,budget.efficiencymay return[]because daily budgets aren't carried in the Apps Script bundle — fall back toperformance.reportcost / conv numbers and rank by CPA. If mureo's Google Ads tools are unavailable (e.g.MUREO_DISABLE_GOOGLE_ADS=1aftermureo providers add google-ads-official), fall back to the officialgoogle-ads-officialMCP for the performance report only, then skipgoogle_ads_budget_efficiency(mureo-only analysis) and rank campaigns by CPA from the raw cost / conv numbers yourself; note to the user that mureo's automated budget-efficiency scoring requires the native MCP (mureo setup claude-code). - Meta Ads: prefer mureo native — call
meta_ads_insights_reportandmeta_ads_analysis_cost. In BYOD mode, daily budgets aren't surfaced — rank by spend ×result_indicator-aware conversions instead. If mureo's Meta Ads tools are unavailable, fall back to the officialmeta-ads-officialhosted MCP for raw insights only, then skipmeta_ads_analysis_cost(mureo-only cost-trend analysis) and theresult_indicator-aware ranking; rank by raw spend / conversions from the official MCP's response instead and warn the user that CV-definition mismatches across campaigns are NOT detected in this fallback path. - mureo BYOD data is centralized in the workspace
byod/directory (or~/.mureo/byod/for legacy CLI users) and is only accessible through mureo MCP tools — do not look for raw CSVs in the project directory.
- Google Ads: prefer mureo native — call
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.
- 5d ago Changed ba1d09d6a819
- 9d ago First seen · 76 lines · 106 tokens per session scan A 6a359548eeb2
budget-rebalance is a skill published in the GitHub repository logly/mureo (44 stars, last pushed 6d ago), licensed Apache-2.0. It adds 106 tokens to every session and 1,877 once invoked, about $0.0005 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 2026-08-30.
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…
adcp-advertising
Automate advertising campaigns with AI. Create ads, buy media, manage ad budgets, discover ad inventory, run display ads, video ads, CTV campaigns, and optimize ad performance. Perfect for marketing automation, programmatic advertising, media buying, ad management, campaign optimization, creative management, and…
google-ads-manager
Google Ads campaign management - campaign setup, keyword research, bid optimization, and performance reporting.
ads-copywriter
Multi-platform ad copy generation for Google Ads, Meta/Facebook, TikTok, LinkedIn with A/B testing variants.
adcp-advertising
Automate advertising campaigns with AI. Create ads, buy media, manage ad budgets, discover ad inventory, run display ads, video ads, CTV campaigns, and optimize ad performance. Perfect for marketing automation, programmatic advertising, media buying, ad management, campaign optimization, creative management, and…
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…