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 repair-orchestratorgit 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/repair-orchestrator)<a href="https://agentmods.dev/skills/xuanranl/loamwright-seo-skill/repair-orchestrator"><img src="https://agentmods.dev/badge/skills/xuanranl/loamwright-seo-skill/repair-orchestrator/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/repair-orchestrator"><img src="https://agentmods.dev/badge/skills/xuanranl/loamwright-seo-skill/repair-orchestrator.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 | $0.00066 | $0.01495 |
| Opus 5 | $0.00033 | $0.00747 |
| Sonnet 5 | $0.00013 | $0.00299 |
| Haiku 4.5 | $0.00007 | $0.00150 |
Grade A, and why
repair-orchestrator 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 12d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repair Orchestrator
The escalating repair pipeline. Driven by quality.json findings.
Inputs
workspace/{task_id}/quality.json(one or more gates failed)workspace/{task_id}/review.json(if independent-reviewer ran)state.repair_iteration(current attempt count; cap = 4)
5 escalation levels
Level 1 — SURGICAL (cheapest, fastest)
Edit specific lines indicated by quality.json.repairs[].instruction
Use Edit tool only (preserve everything else)
If quality improves ≥3 score → progress; loop back at Level 1 again
If improvement <3 → escalate to Level 2
Level 2 — SECTION-REWRITE
Identify which section(s) most contribute to failures
Spawn writer agent for that section with:
- original section spec
- failures list as "things to fix"
- stronger constraints
Re-run quality gates
If still failing → escalate to Level 3
Level 3 — STAGE-REWRITE
Rerun one whole stage of build phase:
- If structural issues: outline-architect (revise outline)
- If reference issues: fact-check-and-citation (verify everything again)
- If voice issues: humanizer (with stricter settings)
Re-run quality gates
If still failing → escalate to Level 4
Level 4 — FULL-REGEN
Rerun all of Phase Build (preserve research.json + angle.json + outline.json)
Re-run quality gates
If still failing → escalate to Level 5
Level 5 — FROM-SCRATCH
Rerun from Plan phase:
- Pick alternative title from angle.alternative_titles_considered
- New outline from scratch
- New writer agents
Re-run quality gates
If still failing → HALT, return best-of-N to user
Hard cap: 4 total rounds across all levels. After round 4, return whatever artifact had highest quality.json score with a documented "could not converge" message.
Decision tree
Read quality.json.repairs[] and quality.gates:
def pick_level(quality, prior_iterations, prior_level):
# First iteration after gate fail
if prior_iterations == 0:
return 1 # Always start surgical
# Surgical didn't improve enough
if prior_level == 1:
# Was improvement small?
delta = current_score - prior_score
if delta < 3:
return 2 # Escalate
return 1 # Continue surgical
# Section rewrite didn't help
if prior_level == 2:
# How many sections needed rewrite?
problem_sections = [s for s in sections if has_issues(s)]
if len(problem_sections) > 3:
return 3 # Stage-level fix
return 2 # Try again
# Stage rewrite didn't help → full regen
if prior_level == 3:
return 4
# Full regen didn't help → from scratch
if prior_level == 4:
return 5
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.
- 12d ago First seen · 184 lines · 66 tokens per session scan A 1e4610cffbca
repair-orchestrator is a skill published in the GitHub repository XuanRanL/loamwright-SEO-Skill (49 stars, last pushed 25d ago), licensed Apache-2.0. It adds 66 tokens to every session and 1,495 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…
competitor-pages
Build competitor comparison and alternatives pages — X-vs-Y head-to-heads, alternatives-to-X lists, category roundups, and feature-matrix pages — delivering a 1,500+ word page template, comparison table, JSON-LD schema via schema-generator.py, keyword and title-tag targeting, an internal-linking plan, and…