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/rohirik/openltm/continuouslearningnpx skills add RohiRIK/OpenLtm --skill continuouslearninggit clone --depth 1 https://github.com/RohiRIK/OpenLtmWhat 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 | $0.00044 | $0.00654 |
| Opus 5 | $0.00022 | $0.00327 |
| Sonnet 5 | $0.00009 | $0.00131 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
ContinuousLearning 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 2d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ContinuousLearning
SQLite-backed memory system at $CLAUDE_PLUGIN_DATA/openltm.db. Two tables: memories (global learned insights) and context_items (per-project goals/decisions/progress/gotchas).
Workflow Routing
| Trigger | Action |
|---|---|
| "Learn this", "Remember this", "Save this pattern" | Run /openltm:memory learn |
| "What do I know about X?", "Any past decisions on Y?" | Run /openltm:memory recall |
| "Forget about X", "That memory is wrong" | Run /openltm:memory forget |
| "X supports Y", "X contradicts Y" | Run /openltm:memory relate |
Recall before non-trivial work and capture genuinely new insights — the goal is automatic retrieval and capture, not a call on every turn. Skip recall for trivial one-liners; skip learn for facts already derivable from the code or git history.
Examples
Example 1 — User asks about past architecture:
User: "What's our caching strategy?" LLM: Calls
recall(query="caching strategy architecture")→ uses results in response.
Example 2 — User discovers a gotcha:
User: "Don't use npm in this project, it's broken with our setup." LLM: Calls
learn(content="Don't use npm - broken with our setup", category="gotcha", importance=4)→ confirms stored.
Example 3 — User starts new feature:
User: "Add auth to the API." LLM: Calls
recall(query="auth")+context(project="api")→ incorporates prior decisions.
Quick Reference
/openltm:memory learn— Store an insight inmemoriestable. Dedup-safe (reinforces on repeat)./openltm:memory recall [query]— FTS5 search with tag/category/project filters./openltm:memory forget <id>— Delete by ID. CASCADE removes relations. Irreversible./openltm:memory relate <src> <tgt> <type>— Link memories. Types:supports|contradicts|refines|depends_on|related_to|supersedes.- Hooks manage context automatically — no manual writes to
context-*.mdfiles needed.
Full Documentation
- Memory commands:
SkillSearch('continuouslearning memory reference')→MemoryReference.md - Hook integration:
SkillSearch('continuouslearning hook integration')→HookIntegration.md - Context item types:
SkillSearch('continuouslearning context items')→ContextItems.md
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 50 lines · 44 tokens per session scan A 6d41533a3402
ContinuousLearning is a skill published in the GitHub repository RohiRIK/OpenLtm (26 stars, last pushed 24d ago), licensed MIT. It adds 44 tokens to every session and 654 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.