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/felipesauer/mnemaWrote 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/felipesauer/mnema/mnema-instructions)<a href="https://agentmods.dev/rules/felipesauer/mnema/mnema-instructions"><img src="https://agentmods.dev/badge/rules/felipesauer/mnema/mnema-instructions/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/felipesauer/mnema/mnema-instructions"><img src="https://agentmods.dev/badge/rules/felipesauer/mnema/mnema-instructions.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 | $0.00606 | $0.00606 |
| Opus 5.5 | $0.00242 | $0.00242 |
| Sonnet 5.5 | $0.00121 | $0.00121 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade C, and why
mnema-instructions scanned grade C with 1 finding 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 3d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- mnema:begin v3 (written by mnema; `mnema instructions --remove` takes it out) --> What it actually says
Recording the work (mnema)
This repository keeps a signed record of its decisions in .mnema/. Where the mnema tools are connected:
- At the start of a session, call
bootstrap: it opens with what is in force, what awaits a judgement and the work in flight. - Before changing a file, call
governing_ruleswith its path. - When a choice is settled, with the person or alone, that someone could later question (a library, an approach, a trade-off, an option turned down), call
record_decisionin that turn, with therationaleand, inalternatives, what was turned down and why. Record it even when it is also written in a plan, a ledger, this file or your own memory. - A decision is born
proposed; once it is accepted it is in force here (an acceptance made by an agent is recorded as an agent’s, andmnema switch off agent-acceptsleaves it to a person). - A decision is not edited once it is recorded. When a new one replaces an earlier one, record the new one and then call
decision_transitionon the earlier one withactionsupersede, the new decision’s id inbyand thereason; the new one is then read as replacing the earlier one, which it names. - A subagent records no decision: it hands its decisions back in its final reply, and the session that started it records them.
- When you learn something about this project that its code does not show, call
capture_memory, also when you keep it in your own memory. - Work in flight is a task (
create_task), and handing work to another agent is a handoff on it (record_handoff), with its brief: the short text, and the path of a file where the brief is long. - Not for the record: each step taken, a credential, personal data, what the code or git already says.
- Commit
.mnema/with the work it describes: the record changes as the work does, through these tools and themnemacommand. Never edit or reformat its files by hand.
Where the tools are not connected and the mnema command is installed, the shell does the same. This records a decision, with what was turned down:
mnema decision record "Use pnpm for the workspace" "The lockfile and the workspace scripts already assume it." --alternatives "npm: no workspace protocol; yarn: a second lockfile to keep"
And this one says a new decision replaces an earlier one:
mnema decision supersede <old-id> <new-id> --reason "<why>"
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.
- 3d ago First seen · 31 lines · 606 tokens per session scan C 53ae32010476
mnema-instructions is a cursor rule published in the GitHub repository felipesauer/mnema (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 606 tokens to every session, about $0.0024 per session on Opus 5.5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-30.
Other cursor rules, from other repositories
bernstein-context
Bernstein governance-layer context - always active when working in a Bernstein-managed project.
orchestration
Guidelines for working in a Bernstein-orchestrated project.
cairn-ground-state
Cairn ground-state awareness — decisions, invariants, and active tasks.
elite-orchestrator
Elite orchestrator for mission-critical, enterprise-scale tasks requiring strategic coordination of 7+ agents across all domains. Makes architectural decisions, manages risk, ensures business continuity, and delivers enterprise-grade outcomes. Use for platform migrations, security incidents, multi-system integrations…
project-onboarding-rule
Automatically onboards existing projects into the AI-driven development workflow.
sprint-planning
BMAD BMM Agent: sprint-planning.