Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Codeprobe

ASecurity

Internal kit of collector — codeprobe.py copies code verbatim for numbered orders and prints their manifest. Not invoked directly — ask collector.

8 stars
0 votes
0 copies
0 views
Added 9/27/2026
ai-agentspythongobashsql

Works with

mcp

Security Analysis

A100/100

Pro scans all 3 files and shows the line behind each finding

Scanned 10/7/2026

$npx -y skills add rezzminator/professor --skill codeprobe --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Codeprobe?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Codeprobe
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rezzminator-codeprobe/badge)](https://www.skillsdirectory.com/skills/rezzminator-codeprobe)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: codeprobe
description: Internal kit of collector — codeprobe.py copies code verbatim for numbered orders and prints their manifest. Not invoked directly — ask collector.
---

# codeprobe

Run `python3 ~/.claude/skills/codeprobe/codeprobe.py {command}`, the path written in full in every command. Python 3 standard library; it reads the repo and writes only under `/tmp/{project}/codeprobe/`. A failure prints `CODEPROBE FAILED — {reason}` and exits 2. Data dumps and fixture records (data files over 200 KB or under a `data/`, `seed/`, `snapshots/`, `dumps/`, `exports/` or `backups/` directory; data and page files under a fixture directory) are counted and never opened.

## Extraction verbs

PATH is relative to ROOT; a directory PATH searches every file under it.

| Verb | Returns |
| --- | --- |
| `file PATH` | The whole file |
| `lines PATH FROM TO` | A range, TO may be `end`; the header names any definition the range cuts through |
| `def PATH NAME…` | Each definition whole, doc comment and decorators included; `Type.method` for a method; a NAME not in PATH is looked up in PATH's directory, then the repo |
| `sig PATH NAME…` | Each signature only |
| `defs PATH [--public] [--containing REGEX]` | Every definition's signature; `--containing` keeps the definitions whose body matches, matching lines marked `*` |
| `block PATH REGEX [-n K]` | The block opening at the K-th matching line: a YAML entry, a SQL statement, a Markdown section, a Makefile target, a brace or indent block |
| `grep REGEX [PATH…] [-C N] [-w] [-i] [-F]` | Every matching line; grep BRE forms `\|`, `\<`, `\>` and `\{n,m\}` are read the way grep reads them; a MISS names the pattern's reading |
| `consts PATH TYPE` | Every constant or variable declared with type TYPE under PATH, iota runs included |

"The columns of table T" is `block MIGRATION 'CREATE TABLE T'` plus `grep 'ALTER TABLE T' MIGRATIONS_DIR`; "the line an insert goes after" is `grep` on that line with `-C 3`.

## collect — the collector's command

```bash
python3 ~/.claude/skills/codeprobe/codeprobe.py collect ROOT --expect 1-2 <<'EOF'
= 1 the Runtime struct in server.go, whole
def pfm/internal/mcpserv/server.go Runtime
= 2 base.py lines 110-236, and the signature of parse_detail
lines src/pkg/adapters/base.py 110 236
sig src/pkg/adapters/base.py parse_detail
EOF
```

`= ID text` opens an order with the caller's own number and words; the lines under it are its commands, one per thing the order names. `--expect` carries the caller's order ids (`1-9`, `1,2,3a`); a plan whose ids differ is refused. The script writes the verbatim text to `DIR/return.md` and prints a manifest, `COLLECTED` to `END`: each order, the `@ path:FROM-TO` header of every block the file holds for it, and each MISS with the nearest names found. First run with a MISS: run `collect ROOT DIR --expect IDS` once more with the whole corrected plan; an order or command the retry drops returns as a MISS, and a third run prints the same manifest again.

Attribution

rezzminatorrezzminator
View sourceSee grades on GitHubMore from rezzminator →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →