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 XuanRanL/loamwright-SEO-Skill --skill resumegit clone --depth 1 https://github.com/XuanRanL/loamwright-SEO-SkillWrote 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/xuanranl/loamwright-seo-skill/resume)<a href="https://agentmods.dev/skills/xuanranl/loamwright-seo-skill/resume"><img src="https://agentmods.dev/badge/skills/xuanranl/loamwright-seo-skill/resume/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/xuanranl/loamwright-seo-skill/resume"><img src="https://agentmods.dev/badge/skills/xuanranl/loamwright-seo-skill/resume.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 | $0.00056 | $0.01038 |
| Opus 5 | $0.00028 | $0.00519 |
| Sonnet 5 | $0.00011 | $0.00208 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
resume 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 11d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resume
The user got interrupted mid-/article (network blip, batch wait, laptop sleep, manual ctrl-C). This skill picks up where it left off.
When to invoke
/resume(defaults to most-recent in-progress task)/resume <task_id>(specific task)- After
/statusshows a stuck or stale task - Auto-suggest in error.json's recovery field
How to invoke
Step 1: Plan the resume (dry-run first)
python -m scripts._core.resume_handler --task-id <id> --dry-run
This outputs:
━━ Resume plan for abc123 ━━━━━━━━━━━━━━━━━
Currently at: build / image-generation-queued
Will resume: build / images-injected
✓ Verified (2):
• image_prompts.json
• batch_id.json
→ Stage complete; jumping to next stage
ETA: 18m42s
Cost left: ~$0.74
Next: Re-invoke L2 phase 'build' for task abc123, resuming at stage 'images-injected'.
Step 2: Execute the resume
Invoke the L2 phase orchestrator named by next_phase in the plan, with the task workspace pointing at the existing one:
next_phase = research→ invokephase-researchSKILL with--resume <task_id>next_phase = plan→ invokephase-buildSKILL with--resume <task_id>next_phase = build→ invokephase-buildSKILL with--resume <task_id>next_phase = optimize→ invokephase-optimizeSKILL with--resume <task_id>next_phase = publish→ invokephase-publishSKILL with--resume <task_id>next_phase = monitor→ invokephase-monitorSKILL with--resume <task_id>
Each L2 reads existing artifacts and skips completed sub-steps (Stage-based guard).
Decision logic (in resume_handler.py)
For task with Stage X:
If all expected artifacts for Stage X exist:
→ jump forward to Stage X+1 (the stage that hadn't started)
Else:
→ re-run Stage X (it didn't finish)
This is deterministic — same input always produces same plan.
When resume is NOT possible
| Condition | Why |
|---|---|
| Task state = "completed" | Nothing to resume |
| Task state = "abandoned" | User explicitly tombstone'd it |
| state.json corrupted / unreadable | No checkpoint to resume from |
| Workspace directory deleted | Same — nothing to resume |
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.
- 11d ago First seen · 121 lines · 56 tokens per session scan A 983b8afa62f6
resume is a skill published in the GitHub repository XuanRanL/loamwright-SEO-Skill (49 stars, last pushed 24d ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,038 once invoked, about $0.0003 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
geo-platform-optimizer
Platform-specific AI search optimization — audit and optimize for Google AI Overviews, ChatGPT, Perplexity, Gemini, and Bing Copilot individually.
continuous-improvement-loop
Run Part 12 of the engagement methodology — the continuous improvement loop that aggregates quarterly-review, customer-feedback, competitive, and operating signals into a Quarterly Product & Offering Improvement Brief for business leadership, plus fast 1-3 page ad-hoc briefs when a significant signal lands…
four-core-documents
Produce Part 3 of the 12-Part engagement: the four strategic-spine documents across 61 steps — 3.1 Business & SBU Analysis, 3.2 Segmentation Framework, 3.3 Brand Positioning & Communications, 3.4 DMFlow — with --doc single-document runs, --view v2 re-runs, and a --combined executive stitch. Triggers on…
seo-plan
Build a 12-month SEO strategy and phased roadmap with industry templates (SaaS, ecommerce, local, publisher, agency). With fresh specialist outputs it runs as a dispatcher: scores four pillars — technical, content, topical, AI search — and makes the weakest pillar the plan's lead theme; missing specialists re-run only…
c2pa-metadata
Embed a C2PA provenance manifest into an AI-generated marketing asset (PNG, JPG, WebP, GIF, TIFF, MP4, MOV, WebM, MP3, WAV, PDF) via scripts/embed-c2pa.py — produces a signed copy of the file carrying IPTC digital-source-type AI claims, an optional c2pa.ai-disclosure assertion for EU AI Act Article 50 (applicable 2…
import-guidelines
Import brand guidelines — voice and tone rules, messaging, banned words and restrictions, channel styles, visual identity — and structure them into enforceable markdown files in the brand's guidelines layer, auto-classified by category, conflict-checked against the brand profile, and merged with existing rules rather…