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/Mnehmos/mnehmos.multi-agent.frameworkWrote 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/mnehmos/mnehmos.multi-agent.framework/_global)<a href="https://agentmods.dev/rules/mnehmos/mnehmos.multi-agent.framework/_global"><img src="https://agentmods.dev/badge/rules/mnehmos/mnehmos.multi-agent.framework/_global/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/mnehmos/mnehmos.multi-agent.framework/_global"><img src="https://agentmods.dev/badge/rules/mnehmos/mnehmos.multi-agent.framework/_global.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00005 | $0.00205 |
| Opus 5.5 | $0.00002 | $0.00082 |
| Sonnet 5.5 | $0.00001 | $0.00041 |
| Haiku 4.5 | $0.00001 | $0.00020 |
Grade A, and why
_global 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 1mo 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
OODA Loop
All work follows: Observe → Orient → Decide → Act
Observe
- Read task/issue fully before coding
- Scan relevant files and test status
- Note dependencies and constraints
Orient
- Map current vs goal state
- Identify risks and unknowns
- Decompose into atomic subtasks
Decide
- Choose lowest-risk approach
- Define scope boundaries
- Set acceptance criteria
Act
- Execute one subtask at a time
- TDD: test first, then implement
- Validate before moving on
TDD Cycle
Red → Failing test defines behavior Green → Minimal code to pass Blue → Refactor while green
Scope Discipline
- Stay within assigned files
- No unrelated modifications
- Escalate ambiguous requirements
- Minimal, surgical changes
Completion
Return: files changed, tests run, summary, open risks
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.
- 1mo ago First seen · 51 lines · 5 tokens per session scan A 264b777bd2f8
_global is a cursor rule published in the GitHub repository Mnehmos/mnehmos.multi-agent.framework (532 stars, last pushed 9mo ago), licensed MIT. It adds 5 tokens to every session and 205 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-08-30.
Other cursor rules, from other repositories
mcpnuke-tests
Test conventions for mcpnuke — enforces TDD workflow.
debug-issue
When the user reports a bug, an error, or unexpected behavior. Enforces four structured phases — reproduction, failing test, root cause isolation, fix and verify — to stop guess-and-check loops.
common-testing
Testing requirements: 80% coverage, TDD workflow.
testing_rules
A testing guide covering TDD, where tests are written before code, and BDD, where expected behavior is described in Given-When-Then form.
tdd
Test-driven development — red-green-refactor cycle.
testing-standards
testing guidelines and expectations.