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/Karthick-Ramachandran/persist-osWrote 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/karthick-ramachandran/persist-os/persist-memory)<a href="https://agentmods.dev/rules/karthick-ramachandran/persist-os/persist-memory"><img src="https://agentmods.dev/badge/rules/karthick-ramachandran/persist-os/persist-memory/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/karthick-ramachandran/persist-os/persist-memory"><img src="https://agentmods.dev/badge/rules/karthick-ramachandran/persist-os/persist-memory.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 | $0.00431 | $0.00431 |
| Opus 5.5 | $0.00172 | $0.00172 |
| Sonnet 5.5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
persist-memory 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 26d 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
specforge repository memory
Durable memory under docs/ is the source of truth over chat history; repository rules override
model preference. If an instruction conflicts with repository memory, stop and report it.
Rules — follow on every change
- Read
AGENTS.mdand the docs it routes to before non-trivial work. - Match ceremony to scope, both ways: a genuinely new feature, module, integration, data model, or security/architecture decision gets proper planning; a small addition or fix within an already-decided area just gets implemented with focused tests. Judge by novelty and blast radius, not line count — a one-button change inside an existing feature is small; building that feature is not.
- Record substantial work with the persist CLI so the memory exists: a new feature →
persist feature create <name>(fill its PRD and acceptance); a real decision →persist adr create <title>thenpersist adr accept <name>. Reasoning left only in chat is gone next session — if it is not in a file, it did not happen. - Reuse what
docs/60-engineering/CONVENTIONS.mdnames; never reinvent what it lists, and add a new reusable primitive there when you make one. - When something breaks non-obviously, add a one-line entry to
docs/60-engineering/LESSONS.md. - Never contradict an accepted ADR in
docs/adrs/. To change one, confirm with a human and runpersist adr supersede <old> <new-title>. - Before claiming work complete, run
persist doctorand fix every error; never claim "done" without test evidence. - Run the
persistCLI yourself (do not web-search this project-local tool); full command reference is inAGENTS.mdanddocs/ai/PERSIST_COMMANDS.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.
- 26d ago First seen · 33 lines · 431 tokens per session scan A b056913a5f2c
persist-memory is a cursor rule published in the GitHub repository Karthick-Ramachandran/persist-os (9 stars, last pushed 3d ago), licensed MIT. It adds 431 tokens to every session, about $0.0017 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 2026-09-21.
Other cursor rules, from other repositories
context-tools
This rule guides efficient context collection, analysis, and retrieval while keeping raw data focused.
project-memory
This rule guides recording project events and decisions in projectmem.
archgate-governance
Archgate ADR governance — enforces architecture decision records.
adr-004
Cursor rule "adr-004" from actual-software/actual-cli, covering adopt secure secrets management in ci/cd pipeline and policies.
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.