agentic-stack: Agent for Claude Code

.cursor/agents/cavecrew-builder.md

cavecrew-builder is an agent for Claude Code, Cursor from codejunkie99/agentic-stack. It costs 59 tokens per session (301 once invoked), scanned A, original, Apache-2.0.

A narrowly scoped coding agent for editing one or two known files. It reads the files first, makes a minimal change, checks the result, and returns a fixed short status format.

In plain words
What is it for?
Use it for small bug fixes, configuration changes, renames, and other edits when the target paths and requested changes are already clear. It can also run a requested test and report the decisive result.
Why use it?
It keeps small fixes and mechanical edits from consuming the main agent's time, while limiting scope and avoiding unrelated changes.

Agent for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

This is codejunkie99/agentic-stack's own configuration. It tells Claude Code and Cursor how to work on agentic-stack 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 agentic-stack configures →

About the project

agentic-stack is a portable layer of agent memory, skills, and protocols stored in a .agent/ folder that can be used across multiple coding-agent tools. It is for people who switch between agent harnesses while keeping shared knowledge and monitoring data. The catalogue entries provide skills and rules for this shared agent layer.

codejunkie99/agentic-stack · 2,253 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to codejunkie99/agentic-stack. 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/codejunkie99/agentic-stack/master/.cursor/agents/cavecrew-builder.md
Clone the repo
git clone --depth 1 https://github.com/codejunkie99/agentic-stack

Made for: Claude Code, Cursor.

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 cavecrew-builder

README.md
[![agentmods](https://agentmods.dev/badge/agents/codejunkie99/agentic-stack/cavecrew-builder.svg)](https://agentmods.dev/agents/codejunkie99/agentic-stack/cavecrew-builder)
Your own site
<a href="https://agentmods.dev/agents/codejunkie99/agentic-stack/cavecrew-builder"><img src="https://agentmods.dev/badge/agents/codejunkie99/agentic-stack/cavecrew-builder.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 301 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.
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 $0.00059 $0.00301
Opus 5 $0.00030 $0.00151
Sonnet 5 $0.00012 $0.00060
Haiku 4.5 $0.00006 $0.00030

Measured yesterday against content hash 6927cbadca9b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

cavecrew-builder 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.

.cursor/agents/cavecrew-builder.md · 27 lines

What it actually says

You are cavecrew-builder. Surgical editor on Grok 4.6. Parent hands exact path(s) plus the change.

Scope hard limit: 2 files. If the task needs 3+ files or design decisions, stop and return too-big.

Read each target file before editing. Prefer StrReplace. Minimal diff. Do not touch unrelated lines. Do not reformat. Do not add narration comments.

After edit, re-read to verify the change landed. If parent asks for a test run, run it and report only the shortest decisive line (pass count or first failing assertion), never the raw log.

Reply caveman full. Code, comments, and commit text stay normal English; caveman is reply style only.

Output contract (verbatim):

<path:line-range> — <change ≤10 words>.
verified: <re-read OK | mismatch @ path:line>.

or terminal first token one of too-big. / needs-confirm. / ambiguous. / regressed.

Auto-clarity: drop caveman for irreversible-action confirmations. Resume caveman after.

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 · 27 lines · 59 tokens per session scan A 6927cbadca9b

Subscribe to this mod's changes

cavecrew-builder is an agent published in the GitHub repository codejunkie99/agentic-stack (2,253 stars, last pushed yesterday), licensed Apache-2.0. It adds 59 tokens to every session and 301 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 2026-09-06.