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.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/codejunkie99/agentic-stacknpx agentmods add rules/codejunkie99/agentic-stack/windsurfrulesWrote 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/rules/codejunkie99/agentic-stack/windsurfrules)<a href="https://agentmods.dev/rules/codejunkie99/agentic-stack/windsurfrules"><img src="https://agentmods.dev/badge/rules/codejunkie99/agentic-stack/windsurfrules.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 | $0.00368 | $0.00368 |
| Opus 5 | $0.00184 | $0.00184 |
| Sonnet 5 | $0.00074 | $0.00074 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
windsurfrules 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 2d 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.
What it actually says
Windsurf rules — agentic-stack portable brain
This project uses a portable brain in .agent/. It is authoritative for
memory, skills, and protocols.
Startup sequence (every session)
- Read
.agent/AGENTS.md - Read
.agent/memory/personal/PREFERENCES.md - Read
.agent/memory/semantic/LESSONS.md - Read
.agent/protocols/permissions.md
Recall before non-trivial tasks
For deploy / ship / release / migration / schema / timestamp / timezone / date / failing test / debug / investigate / refactor, run recall FIRST:
python3 .agent/tools/recall.py "<short description>"
Show surfaced lessons in a Consulted lessons before acting: block and
follow them. This is how graduated lessons cross harnesses.
During work
- Consult
.agent/skills/_index.md. Load a fullSKILL.mdonly when its triggers match the current task (progressive disclosure). - Update
.agent/memory/working/WORKSPACE.mdas the task evolves. - After significant actions, call
python3 .agent/tools/memory_reflect.py <skill> <action> <outcome>. - Quick state:
python3 .agent/tools/show.py. - Teach a rule in one shot:
python3 .agent/tools/learn.py "<rule>" --rationale "<why>".
Hard rules
- Never force push to
main,production, orstaging. - Never delete memory entries; archive only.
- Never modify
.agent/protocols/permissions.md. - When a skill fails 3+ times in 14 days, propose a rewrite rather than repeating the same approach.
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.
- 2d ago First seen · 39 lines · 368 tokens per session scan A 4a14c5fa3905
windsurfrules is a cursor rule published in the GitHub repository codejunkie99/agentic-stack (2,253 stars, last pushed 2d ago), licensed Apache-2.0. It adds 368 tokens to every session, about $0.0018 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 cursor rules, from other repositories
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
context-recorder-system
A modular system for recording project context, decisions, requirements, and lessons in structured files. It divides the recorder into core, template, advanced, and edge-case modules.
self-improving-obsidian-llm-wiki
LLM Wiki OS operating rules.