Borrowing it
Nothing to install: this file belongs to epam/ai-dial-chat. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/epam/ai-dial-chat/development/.claude/skills/refactoring-audit/SKILL.mdgit clone --depth 1 https://github.com/epam/ai-dial-chatWrote 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/epam/ai-dial-chat/refactoring-audit)<a href="https://agentmods.dev/skills/epam/ai-dial-chat/refactoring-audit"><img src="https://agentmods.dev/badge/skills/epam/ai-dial-chat/refactoring-audit.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 54 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Prompt Injection · line 202 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 204 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 206 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00094 | $0.03634 |
| Opus 5 | $0.00047 | $0.01817 |
| Sonnet 5 | $0.00019 | $0.00727 |
| Haiku 4.5 | $0.00009 | $0.00363 |
Grade A, and why
refactoring-audit 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 8d 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Refactoring audit
Produce local-only refactoring plans for this monorepo. Output is planning material for humans — not code changes unless the user explicitly asks to implement something.
Language: All audit outputs MUST be written in English.
Stability rule — no pinned source paths in skill docs
This skill, its templates, and repo-rules-checklist.md describe patterns, thresholds, and grep commands — not specific source file paths. File paths move, split, and get deleted; hardcoded paths in instructions go stale.
- Skill artifacts → patterns + metrics only.
- Audit output docs (
refactoring*.md) → list paths discovered during the current run (fromcollect-metrics.sh+ reads). Regenerate tables each audit; do not copy example paths from templates. - Phase milestones → verify with grep/counts (see Step 4), not memorized filenames.
Outputs (never commit)
| File | Scope |
|---|---|
refactoring.md |
Index + scorecard |
refactoring-backend.md |
apps/chat-api |
refactoring-frontend.md |
apps/chat + hand-authored libs/* |
docs/{change}-openspec-prompt.md |
Only if user wants next OpenSpec prompt |
Git rule: These files MUST stay out of git. After writing, ensure each path is listed in .git/info/exclude. Run git check-ignore -v <file> and confirm git ls-files does not list them. Never git add refactoring docs. Do not add them to .gitignore unless the user explicitly wants team-wide ignore rules in the repo.
When to use
- User asks for refactoring plan, tech-debt review, or codebase analysis
- User asks to refresh refactoring docs after major merges/archives
- User wants backend vs frontend debt split
- Periodic audit (compare with previous
refactoring*.mddate and Δ line counts)
What ships with it
6 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.
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.
- 8d ago First seen · 291 lines · 94 tokens per session scan A c5540519c613
refactoring-audit is a skill published in the GitHub repository epam/ai-dial-chat (504 stars, last pushed today), licensed Apache-2.0. It adds 94 tokens to every session and 3,634 once invoked, about $0.0005 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
requesting-code-review
Pre-commit review: security scan, quality gates, auto-fix.
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
meta-codereview-current-diff
Read the current uncommitted diff, run three independent reviewers (safety + tests-coverage + style) in parallel, then arbitrate a single BLOCK / BLOCKWITHOVERRIDE / PASSWITHNOTES verdict. Use before commit when you want a multi-perspective second-opinion instead of a single-reviewer agent loop.
prs-awaiting-maintainer
List open pull requests where the ball is in the maintainer's court: CI is green and the PR is ready for a maintainer to review, re-review, or merge. Use when the user wants to see PRs awaiting maintainer action.
compliance-checker
Check affiliate content for FTC compliance and platform rules. Triggers on: "check my content for compliance", "FTC disclosure check", "is this legal", "review for compliance", "check affiliate disclosure", "am I FTC compliant", "audit my content", "compliance review", "legal check", "platform rules check", "check…
lean-review
CocoLean diff-scoped over-engineering audit — scans uncommitted git diff and applies five classification tags (delete/stdlib/native/yagni/shrink) to identify unnecessary surface area before commit.