classmap-target

classmap-target is a skill for Claude Code, Codex from LIXianSenQwQ/classmap-skill. It costs 91 tokens per session (1,002 once invoked), scanned A, original, MIT.

A code map in CLASSMAP.md that links features, bugs, and behavior changes to the classes, files, modules, and tests most likely to contain them.

In plain words
What is it for?
Use it to locate where a feature belongs, choose where a bug fix should go, plan a refactor, or find the code responsible for a behavior change.
Why use it?
It reduces blind searching across a repository and helps identify the smallest relevant area before coding. The map is checked against the actual code when it may be incomplete or wrong.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/lixiansenqwq/classmap-skill/classmap-target
Any agent
npx skills add LIXianSenQwQ/classmap-skill --skill classmap-target
Clone the repo
git clone --depth 1 https://github.com/LIXianSenQwQ/classmap-skill

Made for: Claude Code, Codex.

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 classmap-target

README.md
[![agentmods](https://agentmods.dev/badge/skills/lixiansenqwq/classmap-skill/classmap-target.svg)](https://agentmods.dev/skills/lixiansenqwq/classmap-skill/classmap-target)
Your own site
<a href="https://agentmods.dev/skills/lixiansenqwq/classmap-skill/classmap-target"><img src="https://agentmods.dev/badge/skills/lixiansenqwq/classmap-skill/classmap-target.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,002 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00091 $0.01002
Opus 5 $0.00046 $0.00501
Sonnet 5 $0.00018 $0.00200
Haiku 4.5 $0.00009 $0.00100

Measured 4d ago against content hash 304499184ac2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

classmap-target 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.

classmap-target/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

classmap-target

Use CLASSMAP.md as the first navigation layer for AI coding.

The goal is to map the user's request to the smallest accurate set of classes, modules, components, services, controllers, repositories, hooks, stores, APIs, and tests.

Core Rule

Read CLASSMAP.md first.

Do not begin with broad repository search. Use the map to choose likely files, then verify with small focused code reads.

Responsibilities

Use this skill to:

  • Parse the user's requested feature, bug, refactor, or behavior change.
  • Find the most relevant code units from CLASSMAP.md.
  • Explain why each candidate is or is not a target.
  • Read primary target files before searching elsewhere.
  • Use focused search only when the map is missing, incomplete, or suspicious.
  • Implement the requested code change when the user asked for coding.
  • Incrementally update CLASSMAP.md only for files changed, created, or directly verified during this task.

Do not:

  • Rebuild the entire CLASSMAP.md.
  • Scan the whole repository by default.
  • Rewrite unrelated classmap sections.
  • Update entries for files you did not inspect or touch.
  • Treat CLASSMAP.md as authoritative when code contradicts it.
  • Ignore the actual code when the map and code disagree.

Workflow

  1. Parse the request:

    • feature
    • behavior
    • bug symptom
    • domain nouns
    • UI entrypoint
    • API endpoint
    • event, job, or handler
    • data model
    • expected change
  2. Read CLASSMAP.md.

  3. Produce a target recommendation before coding.

  4. Verify by reading primary target files.

  5. Use limited search only if needed:

    • Search for names, methods, routes, events, or concepts discovered from CLASSMAP.md.
    • Avoid broad exploratory search unless CLASSMAP.md is missing or clearly stale.
  6. Make the code change if the user requested implementation.

  7. After code changes, update CLASSMAP.md only for the current task scope.

Target Recommendation Format

Before coding, output a concise routing note:

Read the full file on GitHub · 142 lines

Files

What ships with it

1 file 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.

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. 4d ago First seen · 142 lines · 91 tokens per session scan A 304499184ac2

Subscribe to this mod's changes

classmap-target is a skill published in the GitHub repository LIXianSenQwQ/classmap-skill (3 stars, last pushed 2mo ago), licensed MIT. It adds 91 tokens to every session and 1,002 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 2026-08-31.