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 ericrisco/rsc-harness --skill medium-strategygit clone --depth 1 https://github.com/ericrisco/rsc-harnessWrote 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/ericrisco/rsc-harness/medium-strategy)<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/medium-strategy"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/medium-strategy/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/ericrisco/rsc-harness/medium-strategy"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/medium-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00103 | $0.03414 |
| Opus 5 | $0.00051 | $0.01707 |
| Sonnet 5 | $0.00021 | $0.00683 |
| Haiku 4.5 | $0.00010 | $0.00341 |
Grade A, and why
medium-strategy 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 7d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Medium Strategy — The Account as a Payout System, Not the Next Post
You operate at account + monetization altitude. You decide how a Medium presence becomes a growth and payout system over months: how it earns from the Partner Program, where stories live (your profile, your publication, someone else's), how they win distribution, and what gets repurposed from owned content. You do not draft the article or press the publish button — those are single-story jobs you route out. Mixing altitudes is the fastest way to give generic advice: a portfolio question answered with per-post tactics produces noise.
Your spine is a read/write loop with the account's own history. You read accumulated learnings before deciding and write the decision back, so next quarter compounds instead of restarting from a generic blog post.
Altitude boundary — route single-story work out
| If the ask is… | Route to | Why it is not you |
|---|---|---|
| The article's hook, structure, story, prose | medium-writing |
You decide where it goes and why; writing produces the words. |
| Format one draft, toggle canonical, schedule, submit to a pub's queue | medium-publishing |
You set the cross-post + publication plan; publishing presses the buttons per story. |
| A calendar/repurposing plan across all channels | ../content-engine/SKILL.md |
Multi-platform; you are Medium-only. |
| Push the same post to many networks at once | ../social-publisher/SKILL.md |
Distribution fan-out, not Medium monetization. |
| SEO/canonical mechanics on the owned site the cross-post points back to | ../seo-geo/SKILL.md |
Owned-site SEO; you only set the canonical-import decision. |
| Building a subscriber email list | ../newsletter/SKILL.md |
Medium is not your list. |
1. Read the wiki FIRST — before any decision
Before you recommend anything, read 02-DOCS/wiki/medium/. Why: Medium strategy is iterative; last quarter's Boost hits, accepted-pub list, and tag wins are the only non-generic data you have. Skipping this means re-deriving from blog advice the writer could have Googled.
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.
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.
- 7d ago First seen · 174 lines · 103 tokens per session scan A 183c142f4748
medium-strategy is a skill published in the GitHub repository ericrisco/rsc-harness (81 stars, last pushed today), licensed MIT. It adds 103 tokens to every session and 3,414 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 2026-09-03.
Other skills, from other repositories
build-subgraph
Traverses a full graph and returns a bounded subgraph around one target node -- its depth-bounded dependencies plus any disputed claims attached to it -- while proving everything else was left out.
merge-aliases
Folds two surface names for the same backend system into one canonical entity, keeping every original mention individually retrievable, and refuses to merge pairs that only share spelling.
anchor-and-lock
Consults a check that sits outside the loop system before finalizing any decision the frozen facts bear on, and refuses every attempt by a loop to rewrite a node marked frozen, regardless of how convergent the loop's own reasoning looks.
arbitrate-collision
Detects when two loops have proposed conflicting writes to the same node and field at close to the same time, applies a stated priority rule to accept exactly one, and records the rejected write with the reason it lost.
audit-sweep
Reviews a full set of the main loop's outputs together, from a wider vantage than any single one of them, looking specifically for cross-item patterns that a one-item-at-a-time loop is structurally unable to notice.
trim-to-budget
Trims a task-scoped candidate subgraph down to a hard node-count budget, keeping the anchor plus the highest-relevance nodes, dropping any edge that touches a dropped node, and recording the exact cutoff score used.