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/learnWrote 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/learn)<a href="https://agentmods.dev/skills/logly/mureo/learn"><img src="https://agentmods.dev/badge/skills/logly/mureo/learn/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/learn"><img src="https://agentmods.dev/badge/skills/logly/mureo/learn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 Privilege Escalation · line 63 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- 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.
- medium Excessive Agency · line 91 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00098 | $0.01323 |
| Opus 5.5 | $0.00039 | $0.00529 |
| Sonnet 5.5 | $0.00020 | $0.00265 |
| Haiku 4.5 | $0.00010 | $0.00132 |
Grade A, and why
learn 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.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learn
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).
Save a marketing diagnosis insight to the pro-diagnosis knowledge base.
Saved insights are loaded at the start of future sessions and applied
across /daily-check, /rescue, /budget-rebalance, and the other
diagnostic workflows.
The skill persists insights by shelling out to mureo learn add,
which routes the write through the KnowledgeStore Protocol. The
default backend writes to
~/.claude/skills/_mureo-pro-diagnosis/SKILL.md (preserving the
prior file layout); an alternate backend registered via the
mureo.runtime_context_factory entry-point group can redirect or
split the write without changing this skill.
The knowledge base has two tiers — an operator tier shared across
every workspace, and an optional workspace tier scoped to the
current one. Use mureo learn tiers to find out which are available
before deciding where an insight belongs (step 4).
When to use
- The user runs
/learnfollowed by an insight, e.g.:/learn CV少ないサイトではマイクロCVを活用すべき(sites with few conversions should use micro-conversions)/learn 予算5000円/日で広告グループ8個は多すぎる(eight ad groups is too many on a ¥5,000/day budget)/learn Target CPA を下げすぎると逆に CV が減る(lowering Target CPA too far reduces conversions)
- The user runs
/learnwith no argument — review the current conversation for corrections or marketing expertise the user shared and propose those as insights.
Steps
-
Identify the insight. If the user passed an insight as the argument, use it. Otherwise review the current conversation for moments where the user corrected the agent's analysis or supplied marketing expertise, and select the most reusable one(s).
-
Structure the insight using this template:
### [Short descriptive title] **Situation:** [When this insight applies] **Wrong assumption:** [What an inexperienced agent might think] **Correct approach:** [The right way to handle this situation] **Why:** [The reasoning behind the correct approach] Date learned: YYYY-MM-DD
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.
- yesterday Changed 445f7782c281
- 3d ago Changed 11bde2a1b068
- 5d ago Changed 803351831981
- 6d ago Changed 2cb3322c4b3e
- 22d ago Changed 60e7281b85a8
- 24d ago Changed 0183faf190db
- 26d ago Changed d9992c2eb1ab
- 28d ago Changed 6de4d64fd210
- 1mo ago Changed 90fac286c963
- 1mo ago First seen · 124 lines · 98 tokens per session scan A 96ad2d695608
learn is a skill published in the GitHub repository logly/mureo (51 stars, last pushed today), licensed Apache-2.0. It adds 98 tokens to every session and 1,323 once invoked, about $0.0004 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 2026-08-30.
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.
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…
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…