dev-code-location

A code-location guide for CodeFlowMu projects. It tells a coding agent how to find the right files and documentation before making an edit.

In plain words
What is it for?
Use it to search with rg, identify likely files, check ownership boundaries, and decide whether a task is ready for editing.
Why use it?
It helps prevent changes in the wrong part of the codebase and avoids editing before the task's scope is understood.

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/joinwell52-ai/codeflowmu-open/dev-code-location
Any agent
npx skills add joinwell52-AI/CodeFlowMu-open --skill dev-code-location
Clone the repo
git clone --depth 1 https://github.com/joinwell52-AI/CodeFlowMu-open

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 178 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 $0.00043 $0.00178
Opus 5 $0.00022 $0.00089
Sonnet 5 $0.00009 $0.00036
Haiku 4.5 $0.00004 $0.00018

Measured yesterday against content hash 0a0699a942eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-code-location 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 yesterday.

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.

skills/dev-code-location/SKILL.md · 36 lines

What it actually says

DEV Code Location

When to use

Use before editing code or docs for a DEV task.

Rules

  • Prefer rg and targeted file reads.
  • Read before editing.
  • List candidate files and confidence.
  • Stop if scope or role is unclear.

Required output

Use docs/skills/dev-playbook/code-location.md.

Forbidden actions

  • Do not edit before locating scope.
  • Do not expand into unrelated refactors.
  • Do not overwrite user changes.

Minimal example

Candidate: codeflowmu-shell/src/web-panel.ts
Reason: owns Panel route
Confidence: medium
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. yesterday First seen · 36 lines · 43 tokens per session scan A 0a0699a942eb

Subscribe to this mod's changes

dev-code-location is a skill published in the GitHub repository joinwell52-AI/CodeFlowMu-open (2 stars, last pushed 8d ago), licensed MIT. It adds 43 tokens to every session and 178 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.