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/boparaiamrit/skills-by-amrit/memory-protocolgit clone --depth 1 https://github.com/boparaiamrit/skills-by-amritWrote 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/boparaiamrit/skills-by-amrit/memory-protocol)<a href="https://agentmods.dev/rules/boparaiamrit/skills-by-amrit/memory-protocol"><img src="https://agentmods.dev/badge/rules/boparaiamrit/skills-by-amrit/memory-protocol.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 | $0.00746 | $0.00746 |
| Opus 5 | $0.00373 | $0.00373 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
memory-protocol 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 6d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persistent Memory Protocol
Session Start — ALWAYS DO THIS
At the start of EVERY conversation involving project work:
- Check if
.planning/MEMORY.mdexists in the project root - If it exists, read it silently before doing anything else
- Also read
.planning/handoffs/LATEST.mdif it exists- If LATEST.md doesn't exist, that's OK — skip this step
- Acknowledge context briefly: "From memory: we're working on [X], last session we [Y]"
- Use this context to inform ALL your work in this session
During Session — CAPTURE AS YOU GO
On Significant Decisions
Decisions worth capturing: architecture, technology choices, trade-offs, breaking changes.
Append to .planning/decisions/DECISIONS.md:
## [DATE] — [Topic]
**Decision:** [What was decided]
**Rationale:** [Why]
On Discovering Bugs/Gotchas
Append to .planning/context/gotchas.md:
## [Component]
**Issue:** [Description]
**Workaround:** [How to handle]
On Architecture Changes
Update .planning/context/architecture.md with the change.
Auto-Save Reminder
After completing significant milestones, proactively ask:
"Would you like me to save progress to memory now?"
Session End — ALWAYS DO THIS
When significant work is complete or the user indicates session end:
- Archive previous handoff: Move
LATEST.mdtohandoffs/_history/YYYY-MM-DD-HHMMSS.md - Create session log:
.planning/sessions/YYYY-MM-DD-session-N.md- Session numbering: N = (highest N for today) + 1, or 1 if first session today
- Write handoff:
.planning/handoffs/LATEST.mdwith:- Summary, current state, next steps, blockers, gotchas
- Update
.planning/MEMORY.mdwith new information - Compress if MEMORY.md exceeds 300 lines
Memory Structure
.planning/
├── MEMORY.md # Project brain (~300 lines max)
├── sessions/ # Session logs
│ └── _archive/ # Compressed old sessions
├── decisions/DECISIONS.md # Decision log
├── context/
│ ├── architecture.md # Architecture decisions
│ ├── patterns.md # Code patterns
│ ├── gotchas.md # Known issues
│ └── tech-debt.md # Technical debt
└── handoffs/
├── LATEST.md # Current handoff
└── _history/ # Previous handoffs (archived)
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.
- 6d ago First seen · 91 lines · 746 tokens per session scan A 2e52cf0a1877
memory-protocol is a cursor rule published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 5mo ago), licensed MIT. It adds 746 tokens to every session, about $0.0037 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
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
Context Recorder System (记录员系统) - 模块化索引文件.
memsprout
Cursor rule "memsprout" from memsprout/agents, covering using memsprout, search first, capturing, spaces and topics and files.