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 fjpulidop/specrails-core --skill refactor-recommendergit clone --depth 1 https://github.com/fjpulidop/specrails-coreWrote 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/fjpulidop/specrails-core/refactor-recommender)<a href="https://agentmods.dev/skills/fjpulidop/specrails-core/refactor-recommender"><img src="https://agentmods.dev/badge/skills/fjpulidop/specrails-core/refactor-recommender.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 | $0.00039 | $0.01932 |
| Opus 5 | $0.00019 | $0.00966 |
| Sonnet 5 | $0.00008 | $0.00386 |
| Haiku 4.5 | $0.00004 | $0.00193 |
Grade A, and why
refactor-recommender 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scan the codebase for refactoring opportunities, score each by impact/effort ratio and VPC persona value, and optionally create GitHub Issues for the top findings in the configured backlog provider (read from .specrails/backlog-config.json).
Input: $ARGUMENTS — optional: comma-separated paths to scope the analysis. Flags: --dry-run (print findings without creating issues).
Phase 0: Pre-flight
Check whether the GitHub CLI is available:
Read `.specrails/backlog-config.json` to determine `BACKLOG_PROVIDER` (default: `github`) and `BACKLOG_WRITE` (default: `true`).
- If `BACKLOG_PROVIDER=github`: run `gh auth status`. If it fails, set `BACKLOG_WRITE=false` and warn the user that issues cannot be created.
- If `BACKLOG_PROVIDER=local`: use `.specrails/local-tickets.json` for local issue storage.
- If `BACKLOG_PROVIDER=none`: set `BACKLOG_WRITE=false`.
Set GH_AVAILABLE=true if the command succeeds, GH_AVAILABLE=false otherwise. Do not stop — analysis proceeds regardless. Parse --dry-run from $ARGUMENTS and set DRY_RUN=true if present.
Phase 1: Scope
Parse paths from $ARGUMENTS after stripping any flags. If no paths are provided, scan the entire repository.
Always exclude the following from all analysis:
node_modules/.git/.claude/vendor/dist/build/
Phase 1.5: VPC Context
Check whether persona files exist at .claude/agents/personas/. This path is present in any repo that has run /specrails:setup.
ls .claude/agents/personas/ 2>/dev/null
If the directory exists and contains persona files, set VPC_AVAILABLE=true. Otherwise set VPC_AVAILABLE=false and skip all VPC steps (they are optional enrichment, not blockers).
When VPC_AVAILABLE=true, read each persona file and extract a compact VPC summary. For each persona record:
- name — persona display name (e.g. "Alex — The Lead Dev")
- top_jobs — up to 3 functional jobs relevant to code quality and maintainability
- critical_pains — up to 3 pains marked Critical or High related to code reliability, complexity, or developer experience
- high_gains — up to 3 gains marked High related to code clarity, speed, or confidence
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 · 220 lines · 39 tokens per session scan A 7e4d8c56548d
refactor-recommender is a skill published in the GitHub repository fjpulidop/specrails-core (9 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,932 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
huggingface-vision-trainer
Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for language models.
code-quality
Agents should invoke this skill for code reviews, linting/formatting setup, maintainability checks, complexity concerns, warning cleanup, coding standards, or quality gates in Rust, TypeScript, Python, shell, and mixed repos.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.