Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add rules/codejunkie99/brain/agentic-stackgit clone --depth 1 https://github.com/codejunkie99/brainWhat 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 | $0.00362 | $0.00362 |
| Opus 5 | $0.00181 | $0.00181 |
| Sonnet 5 | $0.00072 | $0.00072 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
agentic-stack 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.
This is a copy
100% identical to agentic-stack — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Agentic-stack brain
This project uses a portable brain in .agent/. Treat it as authoritative.
Before acting
- Read
.agent/AGENTS.md(the map). - Read
.agent/memory/personal/PREFERENCES.md(how the user works). - Read
.agent/memory/semantic/LESSONS.md(what we've learned). - Read
.agent/protocols/permissions.md(what you can and cannot do).
Recall before acting
For any task involving deploy, ship, release, migration, schema change, timestamp / timezone / date, failing test, debug, investigate, or refactor, FIRST run:
python3 .agent/tools/recall.py "<short description of the task>"
If it surfaces lessons, show them in a Consulted lessons before acting:
block and obey them. Without this, graduated lessons stay invisible and the
brain stops compounding.
While working
- Check
.agent/skills/_index.md; load full skills only when triggers match. - Update
.agent/memory/working/WORKSPACE.mdas the task evolves. - After significant actions, run:
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 protected branches.
- Never delete memory entries; archive only.
- Never modify
.agent/protocols/permissions.md.
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 · 42 lines · 362 tokens per session scan A 3473768c7e0f
agentic-stack is a cursor rule published in the GitHub repository codejunkie99/brain (79 stars, last pushed 25d ago), licensed Apache-2.0. It adds 362 tokens to every session, about $0.0018 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to agentic-stack, differing in 0 lines, and is treated as a copy.
Other cursor rules, from other repositories
crystal-memory
Mandatory Memory Crystal discipline for Cursor sessions.
cursorrules
You are using the skill-everything knowledge system: agent memory in plain Markdown, versioned in Git, that grows by capturing your own past mistakes as committed rules.
memory-informed-longitudinal-work
Long-running multi-session work (research, eval loops, iterative benchmarks) — resume prior lessons, capture per-run outcomes, build up stable truths over time.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
memory-informed-refactor
Use before substantive refactors — load relevant prior context, capture refactor insights as they land.
style
Teach your coding agent — Claude Code, Cursor, or any AGENTS.md agent — your project's conventions, and turn every correction into a team-shared, git-tracked lesson.