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 reeswrites/exo --skill recommend-mediagit clone --depth 1 https://github.com/reeswrites/exoWrote 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/reeswrites/exo/recommend-media)<a href="https://agentmods.dev/skills/reeswrites/exo/recommend-media"><img src="https://agentmods.dev/badge/skills/reeswrites/exo/recommend-media/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/reeswrites/exo/recommend-media"><img src="https://agentmods.dev/badge/skills/reeswrites/exo/recommend-media.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 | $0.00083 | $0.01950 |
| Opus 5.5 | $0.00033 | $0.00780 |
| Sonnet 5.5 | $0.00017 | $0.00390 |
| Haiku 4.5 | $0.00008 | $0.00195 |
Grade A, and why
recommend-media 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recommend media
Two answers hide behind one question, and they use different halves of the record. Decide which one is wanted before you call anything.
- From the pile — things they already queued, started and abandoned, or own. Inside the record. This is usually what "what should I watch tonight" means, and the strongest candidates in the whole record live here.
- From outside the pile — something they have not consumed. Discovery. This is what "recommend me something new" means.
When the question does not say, do the pile first and say that is what you did. An abandoned book is a better recommendation than a stranger, and it costs one call to check.
Needs
| tool | without it |
|---|---|
consumption |
you lose the denominator and how current the record is; say the shape is unknown |
medium |
the same in one call, plus the scale and what they own — prefer it when the question names one medium |
ratings |
judge from verdicts and reviews instead, and say the sample is small |
backlog, watching |
the pile route is gone; say so rather than switching routes silently |
taste |
no music membership check and no revealed-preference signal |
taste_summary |
do not call any number high or low. Give it with its scale, flat |
verdicts, reviews |
you have numbers and no reasoning; do not invent why something landed |
collection |
drop the owned-it-already check |
releases |
the only outside pool for music is gone; do not substitute your own |
criticism |
drop the what-is-being-said-now half |
Read the shape before you form a candidate
consumption(medium)— the total andlast_logged. Iflast_loggedis old, every conclusion below is about who they were, not who they are. Say so in the answer rather than quietly discounting it.ratings(medium, order:'recent')— the short-term window. This is what they are like now.taste(order:'recent')— for music, or for cross-domain signal.
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 · 150 lines · 83 tokens per session scan A b4fa836c2eb0
recommend-media is a skill published in the GitHub repository reeswrites/exo (0 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 1,950 once invoked, about $0.0003 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 2026-09-04.
recommend-media compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| recommend-mediareeswrites/exo | Skill | 0 | 1mo ago | MIT | A | 83 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 5d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |