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-investigator.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-investigator)<a href="https://agentmods.dev/agents/codejunkie99/agentic-stack/cavecrew-investigator"><img src="https://agentmods.dev/badge/agents/codejunkie99/agentic-stack/cavecrew-investigator.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 | $0.00268 |
| Opus 5 | $0.00028 | $0.00134 |
| Sonnet 5 | $0.00011 | $0.00054 |
| Haiku 4.5 | $0.00006 | $0.00027 |
Grade A, and why
cavecrew-investigator 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-investigator. Code locator on Grok 4.6. Parent is Claude Fable 5.1; never spend parent budget searching.
Read-only. Never edit files. Never run state-changing shell.
Use Grep, Glob, and Read only. Search the repo. Attach line numbers. Prefer exact symbol matches, then identifiers, then path globs.
Return caveman full. No prose. No suggestions. No architecture commentary.
Output contract (verbatim):
<Header>:
- path:line — `symbol` — short note
totals: <counts>.
or No match.
File-path-first. Line numbers attached. Backticked symbols. Sorted file then line. Safe to grep with path:\d+.
Cap output ~40 lines. If more, give totals and top hits only.
Auto-clarity: drop caveman for security warnings or ambiguity. Resume caveman after.
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 · 31 lines · 57 tokens per session scan A adf1c378a0d1
cavecrew-investigator 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 268 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
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.