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.
git clone --depth 1 https://github.com/Szesnasty/JarvisWrote 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/szesnasty/jarvis/jarvis-agent-rules)<a href="https://agentmods.dev/rules/szesnasty/jarvis/jarvis-agent-rules"><img src="https://agentmods.dev/badge/rules/szesnasty/jarvis/jarvis-agent-rules.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 | $0.00724 | $0.00724 |
| Opus 5 | $0.00362 | $0.00362 |
| Sonnet 5 | $0.00145 | $0.00145 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
jarvis-agent-rules 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jarvis MCP — Agent Rules
MCP server jarvis: notes, Jira, knowledge graph, sessions, preferences.
Rules
- Translate requests into
jarvis_*calls automatically. Never ask user for tool names. - Prefer tools over guesses. Chain tools when needed. If
continuation_token→ calljarvis_continueand merge. - Never hallucinate tool outputs. Empty → say so, propose next query.
Tools (key params)
Search: search_memory(query,top_k,scope) · search_notes(query,top_k) · search_jira(query,top_k)
Notes read: note_read(path) · note_list(folder) · note_outline(path)
Notes write: append_note(path,text) · summarize_and_save(content,path,title) · save_preference(category,rule)
Jira: jira_sprint_risk(sprint,limit) — all issues + risk + bottlenecks + blocked_count · jira_list_issues(project,status,assignee,sprint,limit) — filtered slice · jira_describe_issue(issue_key) · jira_blockers_of(issue_key) · jira_depends_on(issue_key) · jira_cluster_by_topic(project,sprint,max_clusters) — semantic grouping with issue_count
Graph: graph_query(query,top_k) · graph_neighbors(node_id,depth) · graph_entity_detail(node_id) · graph_path_between(from_id,to_id)
Sessions: session_recent(limit,days_back) · session_recent_decisions(days_back) · session_tool_history(days_back)
Meta: workspace_stats · get_preferences(category) · list_specialists · continue(continuation_token)
Routing
- Sprint questions →
jira_sprint_riskfirst. It returnstotal_issues,status_summary,high_risk_count,blocked_count,bottlenecks. Confidence = high. Ifblocked_count=0→ zero blockers, do NOT callsearch_jira("Blocked"). Uselist_issuesonly for filtered slices. - "Zależności/dependencies" → after sprint data, call
graph_neighborson top 2–3 high-risk keys for cross-issue entity connections. - Decisions/history →
session_recent_decisionsfirst, fallbacksearch_memory. - Entity/graph →
search_memorythengraph_neighbors/graph_path_between. - Avoid redundant calls. If the answer is already in the data — stop and answer.
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.
- 8d ago First seen · 36 lines · 724 tokens per session scan A 16ee9d5b6934
jarvis-agent-rules is a cursor rule published in the GitHub repository Szesnasty/Jarvis (10 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 724 tokens to every session, about $0.0036 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 2026-08-31.
Other cursor rules, from other repositories
aionforge-memory
Aionforge Memory cadence and vocabulary — recall first, capture as you go, track tasks as work items.
olympuz
Repository rules for every coding agent.
system-overview
High-level overview of the Adaptive Memory Bank System.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.