tree-sitter-analyzer: Skill for Claude Code

.claude/skills/tsa-edit-then-verify/SKILL.md

tsa-edit-then-verify is a skill for Claude Code from aimasteracc/tree-sitter-analyzer. It costs 267 tokens per session (3,663 once invoked), scanned A, original, MIT.

An edit-and-check workflow for making changes to existing code files. It performs safety and health checks before editing, then checks the diff, assesses impact, and runs a focused verification command.

In plain words
What is it for?
Use it for multi-line code changes when you need pre-edit safety checks, post-edit impact analysis, and scoped tests or other verification.
Why use it?
It catches likely problems without automatically running the full test suite for every change. The focused checks are intended to be quicker while still examining affected code.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is aimasteracc/tree-sitter-analyzer's own configuration. It tells Claude Code how to work on tree-sitter-analyzer itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tree-sitter-analyzer configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/codemap-sync-check.sh.

Reuse

Borrowing it

Nothing to install: this file belongs to aimasteracc/tree-sitter-analyzer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/aimasteracc/tree-sitter-analyzer/main/.claude/skills/tsa-edit-then-verify/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/aimasteracc/tree-sitter-analyzer

Made for: Claude Code.

Wrote 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.

agentmods badge for tsa-edit-then-verify

README.md
[![agentmods](https://agentmods.dev/badge/skills/aimasteracc/tree-sitter-analyzer/tsa-edit-then-verify/github.svg)](https://agentmods.dev/skills/aimasteracc/tree-sitter-analyzer/tsa-edit-then-verify)
Your own site
<a href="https://agentmods.dev/skills/aimasteracc/tree-sitter-analyzer/tsa-edit-then-verify"><img src="https://agentmods.dev/badge/skills/aimasteracc/tree-sitter-analyzer/tsa-edit-then-verify/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.

agentmods 80×15 button for tsa-edit-then-verify

Your own site · 80×15
<a href="https://agentmods.dev/skills/aimasteracc/tree-sitter-analyzer/tsa-edit-then-verify"><img src="https://agentmods.dev/badge/skills/aimasteracc/tree-sitter-analyzer/tsa-edit-then-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 267 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,663 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00267 $0.03663
Opus 5 $0.00133 $0.01832
Sonnet 5 $0.00053 $0.00733
Haiku 4.5 $0.00027 $0.00366

Measured 9d ago against content hash ba76fab3e35d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tsa-edit-then-verify 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 9d 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.

.claude/skills/tsa-edit-then-verify/SKILL.md · 337 lines

How it starts

The opening of the file, as written. The whole thing — 337 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tsa-edit-then-verify — The full edit loop, scoped not full-suite

Source of authority. From docs/agent-tooling-gap-report.md line 58:

Every feature update must run the self-hosted workflow: edit action=safe before risky edits, health action=file on changed files, edit action=impact after edits, its reported verification_command, then the full default suite when risk remains.

This skill is the executable form of that rule. tsa-edit-safety only covers Phase A (the pre-edit gate). This skill covers A + B + C end-to-end and is the canonical replacement for the global verify skill (which runs the full ~5-minute suite every time).

When to use vs. not

Use when you're about to edit (or just edited) a real code file in this repo and the change is more than a 1-line cosmetic fix. The smaller the diff, the bigger the win — full pytest is ~5 min, scoped verification is typically 30-60s.

Don't use for:

  • One-line typo in a doc/comment (no Python AST impact)
  • Pure markdown / README edits (no symbol-level risk)
  • File you're creating from scratch with no callers yet
  • Read-only exploration

Why this exists (vs. verify skill)

Skill What it runs Time When right
verify (global) uv run pytest -q (15k tests) ~5 min Pre-commit gate, large refactor
tsa-edit-then-verify scoped verification_command from edit action=impact 30-60s Every feature update (the mandate)
tsa-edit-safety Pre-edit verdict only ~3s "Is this safe to touch?" — no edit yet

The scoped command targets only the tests reachable from the changed symbols, via the AST call-graph. That's the whole point — edit action=impact returns a verification_command that's narrower than pytest -q but still covers the blast radius the AST sees.

Read the full file on GitHub · 337 lines

Changes

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.

  1. 9d ago First seen · 337 lines · 267 tokens per session scan A ba76fab3e35d

Subscribe to this mod's changes

tsa-edit-then-verify is a skill published in the GitHub repository aimasteracc/tree-sitter-analyzer (49 stars, last pushed today), licensed MIT. It adds 267 tokens to every session and 3,663 once invoked, about $0.0013 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.

Related

Other skills, from other repositories

context7-docs

Fetch up-to-date documentation and code examples for any library, framework, SDK, CLI tool, or cloud service. Use whenever the user asks about a specific library — even well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot — because training data may not reflect recent API changes or…

upstash/context7 · 157 tokens

plan-eng-review

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…

GCWing/BitFun · 116 tokens

autoplan

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when…

GCWing/BitFun · 152 tokens

design-review

Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…

GCWing/BitFun · 125 tokens

pre-landing-review

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues. Use when explicitly asked for the specialized pre-landing workflow. Product /review requests are handled by OpenBitFun's unified Review mechanism instead.…

GCWing/BitFun · 75 tokens

miniapp-dev

A development guide for BitFun MiniApps, which are small applications that run inside BitFun. It covers creating new MiniApps as well as maintaining the MiniApp framework.

GCWing/BitFun · 145 tokens