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 agentmods add skills/rampstackco/claude-skills/content-refresh-systemnpx skills add rampstackco/claude-skills --skill content-refresh-systemgit clone --depth 1 https://github.com/rampstackco/claude-skillsWrote 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/rampstackco/claude-skills/content-refresh-system)<a href="https://agentmods.dev/skills/rampstackco/claude-skills/content-refresh-system"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/content-refresh-system.svg" alt="Measured on agentmods" 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 | $0.00140 | $0.05210 |
| Opus 5 | $0.00070 | $0.02605 |
| Sonnet 5 | $0.00028 | $0.01042 |
| Haiku 4.5 | $0.00014 | $0.00521 |
Grade A, and why
content-refresh-system 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 6d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Refresh System
A senior editorial leader's playbook for systematic content refresh. The discipline that distinguishes intentional refresh programs from set-and-forget decay, and the prioritization framework that prevents both over-refresh (refresh-everything-on-calendar) and under-refresh (refresh-nothing-until-traffic-collapses).
Content decays. Search behavior shifts; SERP intent reshapes; facts go stale; competitors publish stronger pieces; the brand's own positioning evolves past what older pieces represent. Programs that ignore this reality watch traffic erode silently across the library. Programs that overreact (rewriting everything on calendar) burn editorial capacity that should be producing new flagship work. The discipline is in the middle: refresh what matters when signals say so, and document the decisions so the program is auditable.
This skill is the program-level refresh discipline across the whole content library. It builds on pillar-content-architecture's hub-level refresh consideration (refresh as ONE consideration in hub design) and editorial-qa's pre-publish quality gate (this skill is post-publish lifecycle, not pre-publish QA). Together those skills cover content quality at the moments quality decisions get made; this skill covers the moments between, when content is in the field and decaying or holding.
The voice is the senior editorial leader who has watched refresh programs fail in both directions and who has shipped the systems that produced durable refresh discipline.
When to use this skill: building a refresh program from scratch, auditing why refresh work is happening but traffic is not responding, designing the prioritization that keeps refresh tractable across a 200-piece or 2,000-piece library, or fixing a refresh program that is eating editorial capacity without clear results.
What this skill covers
This skill spans the post-publish lifecycle of content. The content suite distinction:
content-strategyis program scope: what to produce.pillar-content-architectureis HUB scope; refresh appears as ONE consideration in hub design.content-brief-authoringis per-piece scope at production time.content-and-copyis execution scope at production time.editorial-qais gate scope: pre-publish verification.content-refresh-system(this skill) is lifecycle scope: program-level refresh discipline across the whole content library, after pieces are in the field.
What ships with it
9 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.
- references/audit-cadence-patterns.md 10 KB
- references/common-refresh-failures.md 11 KB
- references/effectiveness-measurement.md 11 KB
- references/re-promotion-after-refresh.md 10 KB
- references/refresh-depth-decision.md 10 KB
- references/refresh-execution-patterns.md 9.8 KB
- references/refresh-prioritization-matrix.md 11 KB
- references/refresh-signals-checklist.md 10 KB
- references/refresh-vs-merge-vs-delete.md 10 KB
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.
- 6d ago First seen · 262 lines · 140 tokens per session scan A 1365bb8714e2
content-refresh-system is a skill published in the GitHub repository rampstackco/claude-skills (817 stars, last pushed 8d ago), licensed MIT. It adds 140 tokens to every session and 5,210 once invoked, about $0.0007 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
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
workflow
Professional AI programming assistant with structured workflow (Research -> Ideate -> Plan -> Execute -> Optimize -> Review) for developers.
r3f-best-practices
React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
golden-rss
Use when testing the rss golden build.
agile-product-owner
../../../product-team/agile-product-owner/skills/agile-product-owner/SKILL.md.