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 konveyor-ecosystem/playpen-pf-mig-skills --skill migration-comparisongit clone --depth 1 https://github.com/konveyor-ecosystem/playpen-pf-mig-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/konveyor-ecosystem/playpen-pf-mig-skills/migration-comparison)<a href="https://agentmods.dev/skills/konveyor-ecosystem/playpen-pf-mig-skills/migration-comparison"><img src="https://agentmods.dev/badge/skills/konveyor-ecosystem/playpen-pf-mig-skills/migration-comparison/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/konveyor-ecosystem/playpen-pf-mig-skills/migration-comparison"><img src="https://agentmods.dev/badge/skills/konveyor-ecosystem/playpen-pf-mig-skills/migration-comparison.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00046 | $0.01596 |
| Opus 5.5 | $0.00018 | $0.00638 |
| Sonnet 5.5 | $0.00009 | $0.00319 |
| Haiku 4.5 | $0.00005 | $0.00160 |
Grade A, and why
migration-comparison scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Migration Comparison
Compare two different migration attempts of the same codebase (e.g., AI agent A vs ground truth, or agent A vs agent B). Produces a self-contained HTML comparison report with categorized changes, semantic analysis, and side-by-side diffs.
Phase 1: Setup & Validation
1. Collect Inputs
Ask the user for:
- Reference A: git URL with branch (e.g.,
https://github.com/org/repo@branch) or a local directory path. Ask for a label (e.g., "Ground Truth", "Agent A"). - Reference B: same format. Ask for a label.
- File filters (optional): glob patterns to restrict which files are compared (e.g.,
*.tsx,src/**/*.ts). - Migration target (optional): identifier for target-specific pattern scoring (e.g.,
patternfly). When specified, the scoring step uses target-specific pattern detectors for more precise quality scoring.
2. Create Workspace
Create a temporary workspace directory outside either project:
WORK_DIR=$(mktemp -d -t migration-comparison-XXXXXXXX)
All artifacts go inside $WORK_DIR.
3. Validate Inputs
For each reference (A and B):
If local path:
- Verify the directory exists and contains files.
- If the path is invalid or empty, tell the user what is wrong and ask them to provide a corrected path.
If git URL:
- Attempt:
git clone --branch <branch> --depth 1 <url> $WORK_DIR/<label> - If the clone fails (auth error, invalid URL, branch not found, network issue), show the user the error and ask:
- Provide a corrected URL/branch
- Provide a local path instead
- Abort
- If the branch is not found, run
git ls-remote --heads <url>to list available branches and show them to the user.
4. Check Tool Availability
Run:
python3 scripts/run_diffs.py --check-gumtree
This returns JSON: {"available": true/false, "method": "native|podman|docker|none", "version": "..."}.
If GumTree is not available, inform the user and ask:
- Continue with text-only diffing (still produces a useful report, just without AST-level semantic categorization)
- Install GumTree first (
podman pull gumtreediff/gumtree,docker pull gumtreediff/gumtree, or download from GitHub releases) - Abort
What ships with it
22 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.
- progress.txt 7.7 KB
- README.md 7.6 KB
- scripts/.gitignore 7 B
- scripts/ast_helpers.py 8.5 KB runs code
- scripts/categorize_changes.py 10 KB runs code
- scripts/compose_evaluation.py 24 KB runs code
- scripts/enumerate_files.py 7.5 KB runs code
- scripts/generate_comparison_report.py 38 KB runs code
- scripts/generate_evaluation_report.py 65 KB runs code
- scripts/generate_markdown_report.py 14 KB runs code
- scripts/llm_prompts.py 14 KB runs code
- scripts/models.py 7.3 KB runs code
- scripts/requirements.txt 62 B
- scripts/run_diffs.py 14 KB runs code
- scripts/run_evaluation.py 9.0 KB runs code
- scripts/run_full_evaluation.py 7.0 KB runs code
- scripts/run_llm_review.py 18 KB runs code
- scripts/run_pipeline.sh 622 B runs code
- scripts/score_migration.py 39 KB runs code
- targets/__init__.py 0 B runs code
- targets/patternfly_patterns.py 50 KB runs code
- targets/patternfly_runtime.yaml 1.8 KB
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.
- 1mo ago First seen · 181 lines · 0 tokens per session scan A 1c6d5e8160da
migration-comparison is a skill published in the GitHub repository konveyor-ecosystem/playpen-pf-mig-skills (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,596 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…