claude-vibe-squad: Skill for Claude Code

.agents/skills/code-reachability-audit/SKILL.md

code-reachability-audit is a skill for Claude Code, Codex from mtarcure/claude-vibe-squad. It costs 66 tokens per session (1,056 once invoked), scanned A, original, MIT.

A repository search guide for deciding whether a file or script is still used. It checks code, automation, configuration, documentation, and scheduled jobs for callers.

In plain words
What is it for?
Use it before calling a repository file dead or proposing its deletion. It helps classify how a file is reached and document the evidence.
Why use it?
It helps avoid deleting something that appears unused but is still run indirectly. It also separates real usage from misleading mentions in comments or documentation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is mtarcure/claude-vibe-squad's own configuration. It tells Claude Code and Codex how to work on claude-vibe-squad 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 claude-vibe-squad configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mtarcure/claude-vibe-squad. 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/mtarcure/claude-vibe-squad/main/.agents/skills/code-reachability-audit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mtarcure/claude-vibe-squad

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 code-reachability-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/code-reachability-audit.svg)](https://agentmods.dev/skills/mtarcure/claude-vibe-squad/code-reachability-audit)
Your own site
<a href="https://agentmods.dev/skills/mtarcure/claude-vibe-squad/code-reachability-audit"><img src="https://agentmods.dev/badge/skills/mtarcure/claude-vibe-squad/code-reachability-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,056 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 warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high YARA Match · line 25
    YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).
    Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.
  • medium Rogue Agent · line 24
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 25
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 $0.00066 $0.01056
Opus 5 $0.00033 $0.00528
Sonnet 5 $0.00013 $0.00211
Haiku 4.5 $0.00007 $0.00106

Measured 8d ago against content hash bc0c33d8c89d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

code-reachability-audit 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 8d 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.

.agents/skills/code-reachability-audit/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reachability Audit

Deciding a file is dead is a deletion, and deletions are irreversible. The claim "nothing calls this" is an absence claim, so it needs an exhaustive search plus a control proving the search can detect presence. A grep miss is not proof.

The search set — every surface, not just the obvious ones

A repo-only git grep is not exhaustive. Check all of these:

Surface Why it hides callers
Shell exec, source, bash "$VAR", paths built from $(dirname …)
Python subprocess, Path(...), names assembled from parts
.github/workflows/** CI is a caller with no in-repo reference to it
Git hooks (.githooks/**) invoked by git, never by code
Plugin manifests, lane adapters declarative wiring, not calls
~/Library/LaunchAgents/*.plist outside the repo entirely
crontab -l, systemd units same class as launchd on other platforms
Operator documentation a script a human runs on purpose is live with zero programmatic callers

The launchd surface is the one that bites. On 2026-08-06 an audit classified bin/squad-monitor.sh as dead on correct in-repo evidence — its only references were two tests. It runs every 120 seconds via com.chrono.squad-monitor, registered in ~/Library/LaunchAgents/, where no git grep reaches. Six repo scripts are bound that way. bin/doctor.sh now reports the mapping on every health run; read it before calling anything dead.

Matching, without fooling yourself

Both failure directions are real and both happened in one session:

  • Too loose. A bare basename search reported capture.py as having six callers. Every hit was inside autocapture.py.
  • Too strict. Anchoring with [^A-Za-z0-9_/-] then excluded /, hiding path-qualified references, so a file with a live caller looked orphaned.

Use (^|[^A-Za-z0-9_-])<basename> — allow a path separator before the name, forbid word characters.

Two controls, every time

Read the full file on GitHub · 89 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. 8d ago First seen · 89 lines · 66 tokens per session scan A bc0c33d8c89d

Subscribe to this mod's changes

code-reachability-audit is a skill published in the GitHub repository mtarcure/claude-vibe-squad (109 stars, last pushed 2d ago), licensed MIT. It adds 66 tokens to every session and 1,056 once invoked, about $0.0003 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