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 agentmods add skills/yailperalta/ast-mcp-server/structural-code-editingnpx skills add yailPeralta/ast-mcp-server --skill structural-code-editinggit clone --depth 1 https://github.com/yailPeralta/ast-mcp-serverWrote 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/yailperalta/ast-mcp-server/structural-code-editing)<a href="https://agentmods.dev/skills/yailperalta/ast-mcp-server/structural-code-editing"><img src="https://agentmods.dev/badge/skills/yailperalta/ast-mcp-server/structural-code-editing.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 | $0.00037 | $0.00928 |
| Opus 5 | $0.00018 | $0.00464 |
| Sonnet 5 | $0.00007 | $0.00186 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
structural-code-editing 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 4d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Edición estructural con el servidor MCP ast
Activation Contract
Cargar este skill antes de navegar semánticamente, analizar impacto o referencias, consultar diagnostics o preparar una mutación TypeScript/JavaScript gobernada por el compilador.
No forzar un roundtrip AST para Markdown, configuración, comentarios ni una edición textual trivial en un archivo ya conocido. Si las tools ast_* no están disponibles, declarar el fallback y no presentar búsquedas textuales como evidencia compiler-backed.
Published v0.12.0 requires Node.js >=22.13.0 and retains immutable release evidence from exact Node.js 22.13.0 plus the governed Node.js 24 line.
Hard Rules
- Verificar primero que las tools existen y que
ast_get_project_statusinforma un proyecto usable. - Tratar como autoritativa solo evidencia
compiler+exact+resolved+fresh. - Revisar siempre límites,
completeness,unresolvedytruncationantes de inferir ausencia. - Preparar mutaciones, revisar preview y diagnostics, y aplicar únicamente con el
operation_idyplan_hashexactos. - Nunca reconstruir postimages desde un diff; después del apply, ejecutar el gate canónico del proyecto.
- Conservar
correlation_iden errores públicos sin exponer source, paths absolutos, argumentos, environment, cache, stacks ni credenciales.
Diagnostic aggregates
ast_get_diagnostics keeps its existing response shape unless include_aggregates: true is requested. Enabled summaries cover the complete normalized snapshot, not only the selected raw page, and cap both code and file groups at 20.
For each dimension, groups.length + omitted_group_count = total_group_count and group counts sum to covered_diagnostic_count. Code coverage plus omitted diagnostics equals the total; file coverage additionally includes unfiled_diagnostic_count. File groups expose normalized project-relative paths only and may include paths absent from the raw page.
Contributor contract
Al agregar o modificar una tool, mantener schemas, metadata, annotations, handler, errores y serialización en su módulo. Exportar un descriptor congelado y ubicarlo deliberadamente en src/tools/catalog.ts; el catálogo solo admite hechos estáticos de efecto, batch, compatibilidad y formatos directos.
What ships with it
3 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.
- 4d ago First seen · 68 lines · 37 tokens per session scan A df2ebc3f3903
structural-code-editing is a skill published in the GitHub repository yailPeralta/ast-mcp-server (4 stars, last pushed today), licensed ISC. It adds 37 tokens to every session and 928 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
cc10x-router
THE ONLY ENTRY POINT FOR CC10X. Activate this skill for build, debug, review, and plan requests. Use when the user asks to implement, fix, review, plan, test, refactor, or continue code work. Trigger keywords: build, implement, create, write, add, review, audit, debug, fix, error, bug, broken, plan, design, architect…
building
Implementation skill for writing production code with TDD. Covers the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns. Loaded by component-builder and bug-investigator.
diff-driven-docs
Use when a BUILD phase completes, a commit is staged, or a PR is about to be created, and the diff has not yet been reflected in documentation. Also use when the user says "update docs", "sync docs", "document this", or asks whether documentation is up to date.
exploration
Two-mode exploration skill: (1) design dialogue — turn rough ideas into validated designs through collaborative interview before planning; (2) spike — throwaway code answering ONE design question, deleted or absorbed, never shipped. Router invokes mode via dispatch context.
memory-and-handoff
Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.
plan-review-gate
Use after saving a non-trivial plan or decision RFC when a fail-closed feasibility, completeness, and alignment review must block execution.