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 calm-north/seojuice-skills --skill recover-contentgit clone --depth 1 https://github.com/calm-north/seojuice-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/calm-north/seojuice-skills/recover-content)<a href="https://agentmods.dev/skills/calm-north/seojuice-skills/recover-content"><img src="https://agentmods.dev/badge/skills/calm-north/seojuice-skills/recover-content/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/calm-north/seojuice-skills/recover-content"><img src="https://agentmods.dev/badge/skills/calm-north/seojuice-skills/recover-content.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk 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 | $0.00059 | $0.02204 |
| Opus 5.5 | $0.00024 | $0.00882 |
| Sonnet 5.5 | $0.00012 | $0.00441 |
| Haiku 4.5 | $0.00006 | $0.00220 |
Grade A, and why
recover-content 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recover Content
Diagnose and reverse traffic loss on existing pages using the decay triage framework: refresh, consolidate, redirect, or retire.
Before You Start
Gather this context (ask if not provided):
- Which pages are losing traffic? Specific URLs or a general "the whole blog is declining."
- How much traffic was lost? Percentage drop or absolute numbers.
- Over what timeframe? Gradual decline over months vs sudden drop.
- Any recent changes? Site redesign, CMS migration, content edits, algorithm update timing.
If the user doesn't know which pages are declining, suggest checking Google Search Console → Performance → Pages, sorted by click change over the last 6 months.
Identifying Decay
Content decay happens when a page gradually loses search traffic over time. Common signals:
- Clicks declining month-over-month for 3+ months
- Position slipping from page 1 to page 2+
- Impressions stable but CTR dropping (competitors have better titles/snippets)
- Impressions declining (Google no longer considers the page relevant)
Composite Decay Score
Score each page across 5 weighted signals to prioritize action:
| Signal | Weight | How to Score (0-100) |
|---|---|---|
| Traffic decline | 30% | 0 = no decline, 50 = 20-40% drop, 100 = >60% drop |
| Position drops | 25% | 0 = stable, 50 = lost 3-5 positions, 100 = dropped off page 1 |
| CTR decline | 15% | 0 = stable, 50 = 20% decline, 100 = >40% decline |
| Content freshness | 15% | 0 = updated this quarter, 50 = 6-12 months stale, 100 = >2 years stale |
| Competitive displacement | 15% | 0 = no new competitors, 50 = new entrants on page 1, 100 = displaced from top 3 |
Composite Decay Score = (Traffic x 0.30) + (Position x 0.25) + (CTR x 0.15)
+ (Freshness x 0.15) + (Displacement x 0.15)
| Score | Stage | Response |
|---|---|---|
| 0-20 | Healthy | Continue monitoring |
| 21-40 | Early decay | Add to refresh queue (next month) |
| 41-60 | Active decay | Schedule refresh this week |
| 61-80 | Significant decay | Immediate refresh or rewrite decision |
| 81-100 | Terminal decay | Rewrite, redirect, or retire |
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 · 234 lines · 59 tokens per session scan A 0254e0ab43cf
recover-content is a skill published in the GitHub repository calm-north/seojuice-skills (21 stars, last pushed 8mo ago), licensed MIT. It adds 59 tokens to every session and 2,204 once invoked, about $0.0002 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.
recover-content compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| recover-contentcalm-north/seojuice-skills | Skill | 21 | 8mo ago | MIT | A | 59 | Claude Code, Codex |
| content-amplifieraaron-he-zhu/aaron-marketing-skills | Skill | 3.1k | yesterday | Apache-2.0 | A | 202 | Claude Code |
| cold-outbound-sequenceraaron-he-zhu/aaron-marketing-skills | Skill | 3.1k | yesterday | Apache-2.0 | A | 172 | Claude Code |
| inbox-placement-monitoraaron-he-zhu/aaron-marketing-skills | Skill | 3.1k | yesterday | Apache-2.0 | A | 166 | Claude Code |
| newsletter-monetization-planneraaron-he-zhu/aaron-marketing-skills | Skill | 3.1k | yesterday | Apache-2.0 | A | 139 | Claude Code |
| audience-mapperaaron-he-zhu/aaron-marketing-skills | Skill | 3.1k | yesterday | Apache-2.0 | A | 156 | Claude Code |
| pricing-packaging-planneraaron-he-zhu/aaron-marketing-skills | Skill | 3.1k | yesterday | Apache-2.0 | A | 166 | Claude Code |