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 pproenca/dot-skills --skill codemodgit clone --depth 1 https://github.com/pproenca/dot-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/pproenca/dot-skills/codemod)<a href="https://agentmods.dev/skills/pproenca/dot-skills/codemod"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/codemod/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/pproenca/dot-skills/codemod"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/codemod.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 | $0.00081 | $0.01872 |
| Opus 5 | $0.00041 | $0.00936 |
| Sonnet 5 | $0.00016 | $0.00374 |
| Haiku 4.5 | $0.00008 | $0.00187 |
Grade A, and why
codemod 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 5d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codemod Best Practices
Comprehensive best practices guide for Codemod (JSSG, ast-grep, workflows), designed for AI agents and LLMs. Contains 48 rules across 11 categories, prioritized by impact to guide automated refactoring and code generation.
When to Apply
Reference these guidelines when:
- Writing new codemods with JSSG or ast-grep
- Designing workflow configurations for migrations
- Debugging pattern matching or AST traversal issues
- Reviewing codemod code for performance and safety
- Setting up test fixtures for transform validation
Rule Categories by Priority
| Priority | Category | Impact | Prefix |
|---|---|---|---|
| 1 | AST Understanding | CRITICAL | ast- |
| 2 | Pattern Efficiency | CRITICAL | pattern- |
| 3 | Parsing Strategy | CRITICAL | parse- |
| 4 | Node Traversal | HIGH | traverse- |
| 5 | Semantic Analysis | HIGH | semantic- |
| 6 | Edit Operations | MEDIUM-HIGH | edit- |
| 7 | Workflow Design | MEDIUM-HIGH | workflow- |
| 8 | Testing Strategy | MEDIUM | test- |
| 9 | State Management | MEDIUM | state- |
| 10 | Security and Capabilities | LOW-MEDIUM | security- |
| 11 | Package Structure | LOW | pkg- |
Quick Reference
1. AST Understanding (CRITICAL)
ast-explore-before-writing- Use AST Explorer before writing patternsast-understand-named-vs-anonymous- Understand named vs anonymous nodesast-use-kind-for-precision- Use kind constraint for precisionast-field-access-for-structure- Use field access for structural queriesast-check-null-before-access- Check null before property access
2. Pattern Efficiency (CRITICAL)
pattern-use-meta-variables- Use meta variables for flexible matchingpattern-avoid-overly-generic- Avoid overly generic patternspattern-combine-with-rules- Combine patterns with rule operatorspattern-use-constraints- Use constraints for reusable matching logicpattern-use-relational-patterns- Use relational patterns for contextpattern-ensure-idempotency- Ensure patterns are idempotent
What ships with it
53 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.
- AGENTS.md 10.0 KB
- assets/templates/_template.md 871 B
- metadata.json 943 B
- README.md 4.4 KB
- references/_sections.md 2.5 KB
- references/ast-check-null-before-access.md 1.8 KB
- references/ast-explore-before-writing.md 1.5 KB
- references/ast-field-access-for-structure.md 1.7 KB
- references/ast-understand-named-vs-anonymous.md 1.5 KB
- references/ast-use-kind-for-precision.md 1.4 KB
- references/edit-add-imports-correctly.md 2.1 KB
- references/edit-batch-before-commit.md 1.7 KB
- references/edit-handle-overlapping-ranges.md 2.1 KB
- references/edit-preserve-formatting.md 2.2 KB
- references/edit-use-flatmap-for-conditional.md 2.0 KB
- references/parse-early-return-non-applicable.md 2.0 KB
- references/parse-handle-embedded-languages.md 2.2 KB
- references/parse-provide-pattern-context.md 1.9 KB
- references/parse-select-correct-parser.md 1.8 KB
- references/pattern-avoid-overly-generic.md 1.5 KB
- references/pattern-combine-with-rules.md 1.8 KB
- references/pattern-ensure-idempotency.md 2.0 KB
- references/pattern-use-constraints.md 1.7 KB
- references/pattern-use-meta-variables.md 1.6 KB
- references/pattern-use-relational-patterns.md 1.7 KB
- references/pkg-organize-by-convention.md 1.9 KB
- references/pkg-use-semantic-versioning.md 1.7 KB
- references/pkg-write-descriptive-metadata.md 1.7 KB
- references/security-minimize-capabilities.md 1.7 KB
- references/security-review-before-running-third-party.md 1.7 KB
- references/security-validate-external-inputs.md 1.8 KB
- references/semantic-cache-cross-file-results.md 2.3 KB
- references/semantic-check-null-results.md 2.0 KB
- references/semantic-use-file-scope-first.md 2.1 KB
- references/semantic-verify-file-ownership.md 2.3 KB
- references/state-log-progress-for-observability.md 2.0 KB
- references/state-make-transforms-idempotent.md 1.8 KB
- references/state-use-for-resumability.md 1.7 KB
- references/test-cover-edge-cases.md 1.8 KB
- references/test-run-on-subset-first.md 1.6 KB
- references/test-update-fixtures-intentionally.md 1.6 KB
- references/test-use-fixture-pairs.md 1.6 KB
- references/test-use-strictness-levels.md 1.8 KB
- references/traverse-cache-repeated-lookups.md 1.8 KB
- references/traverse-single-pass-collection.md 1.9 KB
- references/traverse-use-find-vs-findall.md 1.5 KB
- references/traverse-use-siblings-efficiently.md 1.8 KB
- references/traverse-use-stopby-for-depth.md 1.8 KB
- references/workflow-order-nodes-by-dependency.md 1.8 KB
- references/workflow-use-conditional-steps.md 2.0 KB
- references/workflow-use-manual-gates.md 1.8 KB
- references/workflow-use-matrix-for-parallelism.md 2.0 KB
- references/workflow-validate-before-run.md 1.5 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.
- 5d ago First seen · 128 lines · 81 tokens per session scan A 40ec28d16cc6
codemod is a skill published in the GitHub repository pproenca/dot-skills (205 stars, last pushed 24d ago), licensed MIT. It adds 81 tokens to every session and 1,872 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
experimental-code-coverage-local-debugger
Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.