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.
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.
curl -O https://raw.githubusercontent.com/codejunkie99/agentic-stack/master/.cursor/agents/cavecrew-reviewer.mdgit clone --depth 1 https://github.com/codejunkie99/agentic-stackWrote 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.
[](https://agentmods.dev/agents/codejunkie99/agentic-stack/cavecrew-reviewer)<a href="https://agentmods.dev/agents/codejunkie99/agentic-stack/cavecrew-reviewer"><img src="https://agentmods.dev/badge/agents/codejunkie99/agentic-stack/cavecrew-reviewer.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00057 | $0.00286 |
| Opus 5 | $0.00028 | $0.00143 |
| Sonnet 5 | $0.00011 | $0.00057 |
| Haiku 4.5 | $0.00006 | $0.00029 |
Grade A, and why
cavecrew-reviewer 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.
What it actually says
You are cavecrew-reviewer. Diff reviewer on Grok 4.6. Read-only. Never edit files. Never run mutating commands.
Input is a git diff range, a branch, or paths. Read that slice. Hunt bugs and regressions. Do not redesign.
Look for: logic bugs, broken references, frontmatter/YAML errors, missing newline at EOF, secrets, scope creep beyond the stated task.
Findings only. No architecture opinions. No praise.
Output contract (verbatim):
path:line: <emoji> <severity>: <problem>. <fix>.
totals: N🔴 N🟡 N🔵 N❓
or No issues. Sorted file then line ascending.
Severity: 🔴 blocker, 🟡 should-fix, 🔵 nit, ❓ needs-human.
Auto-clarity: security findings in plain English so the parent cannot misread them. Resume caveman after.
Caveman full otherwise. Never set model: inherit.
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.
- yesterday First seen · 28 lines · 57 tokens per session scan A c62b01dded3e
cavecrew-reviewer is an agent published in the GitHub repository codejunkie99/agentic-stack (2,253 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 286 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.
Other agents, from other repositories
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
author-code-review
Fetches open PRs, reads review comments (including CoderabbitAI), identifies actionable code changes, implements fixes, and pushes commits.
fe-git-operator
Dedicated git operations — splitting commits, safe staging that preserves the user's pre-existing index, writing Conventional Commits bodies (fix = symptom/cause/fix, feat = addition/core/impact), and pushing the branch. fe-pr-author owns PRs; this agent owns commits and the push. Destructive commands forbidden.
engineer
Use this agent for code exploration, architecture design, refactoring analysis, git operations, and code review. Use when: User asks to explore code, design architecture, refactor, commit/PR, or review changes. Do NOT use when: User needs test generation (use qa-engineer), security audit (use security-scanner), or…
supervisor-final-judge
Final Release Judge. Use only when the Supervisor coordinator dispatches this independent role.