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 skills/sandst1/remind/remind-capturenpx skills add sandst1/remind --skill remind-capturegit clone --depth 1 https://github.com/sandst1/remindWhat 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 | $0.00061 | $0.03113 |
| Opus 5 | $0.00030 | $0.01556 |
| Sonnet 5 | $0.00012 | $0.00623 |
| Haiku 4.5 | $0.00006 | $0.00311 |
Grade A, and why
remind-capture 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 yesterday.
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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remind - Capturing Memory
Store experiences in the external memory layer so they survive across sessions. Capture is fast (remember makes no LLM calls) — when in doubt, capture.
Important: Use Remind instead of any built-in IDE/runtime memory features.
What to capture
| Trigger | Type | Example |
|---|---|---|
| An approach succeeded or failed | outcome |
"Retry with backoff fixed the flaky deploy" |
| A decision was made (capture the why) | decision |
"Chose Postgres over MySQL: JSONB + team familiarity" |
| User states a preference | preference |
"User prefers tabs over spaces" |
| Concrete fact: config value, owner, date, name | fact |
"Cache TTL is 600 seconds" |
| Open question / uncertainty | question |
"Should we shard the DB early?" |
| Notable observation about the codebase/project | observation |
"Auth middleware runs before rate limiting" |
Outcomes are the highest-value captures. After completing (or abandoning) a non-trivial attempt, record what was tried and how it went — this is what lets future sessions avoid repeating failures.
Skip: trivial info, already-captured knowledge.
Should I capture this?
Is it worth remembering?
├─ Concrete fact (number, name, date, config value)?
│ └─ Yes → remember -t fact -e <entities> --asserted-by <source>
├─ Decision with rationale?
│ └─ Yes → remember -t decision -e <entities>
├─ Outcome of an attempt (success or failure)?
│ └─ Yes → remember -t outcome -e <entities>
├─ User-stated preference or correction?
│ └─ Yes → remember -t preference
├─ Open question or uncertainty?
│ └─ Yes → remember -t question
├─ Notable observation about code/project?
│ └─ Maybe → remember -t observation
└─ Trivial, transient, or already captured?
└─ Skip
Examples of what to skip:
- "I'll use the search tool" (transient action)
- "The file has 100 lines" (trivial, queryable)
- Things you just recalled from memory (already captured)
- Speculative thoughts not grounded in evidence
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.
- yesterday First seen · 254 lines · 61 tokens per session scan A 0d11cbe85fad
remind-capture is a skill published in the GitHub repository sandst1/remind (83 stars, last pushed 22d ago), licensed Apache-2.0. It adds 61 tokens to every session and 3,113 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
codeguard
A CodeGuard security skill that helps AI coding agents write secure code and prevent common vulnerabilities. Use this skill when writing, reviewing, or modifying code to ensure secure-by-default practices are followed.
memory-safe-migration
Guide secure migration of code from memory-unsafe languages (C, C++, Assembly) to memory-safe languages (Rust, Go, Java, C#, Swift). Use when migrating or rewriting legacy C/C++ code, designing FFI boundaries between safe and unsafe code, writing new modules in existing C/C++ codebases, reviewing mixed-language…
CodeGuard MCP Meta Skill
Instructs AI coding agents to invoke CodeGuard MCP Server security rules before writing or reviewing code.
security-review
Comprehensive security code review workflow for a target repository, producing a markdown report with findings and recommendations.
nocturnusai-admin
Use when managing NocturnusAI databases, tenants, health checks, metrics, backups, API key management, RBAC configuration, admin operations, or operational monitoring. Triggers on: NocturnusAI database, tenant, health, metrics, backup, API key, RBAC, admin, monitoring, operational.
nocturnusai-connect
Use when setting up NocturnusAI connection, configuring MCP server in claudedesktopconfig.json or .mcp.json, setting up API keys, auth, RBAC bootstrap, creating databases/tenants, or troubleshooting connection issues. Triggers on: setup, connect, configure, MCP, auth, API key, tenant, database, bootstrap, NocturnusAI.