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/session-contextnpx skills add RohiRIK/OpenLtm --skill session-contextgit 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 | $0.00037 | $0.00989 |
| Opus 5 | $0.00018 | $0.00495 |
| Sonnet 5 | $0.00007 | $0.00198 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
session-context 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 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.
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Context Persistence
Overview
Per-project context lives in $CLAUDE_PLUGIN_DATA/openltm.db (SQLite). Hooks manage it automatically.
Project names come from ~/.claude/projects/registry.json — run /openltm:project register to see yours.
Claude does NOT manually write context files. Hooks handle all reads and writes.
The 4 Context Types
| Type | Purpose | Managed by |
|---|---|---|
goal |
Current objective (1-3 lines) | /openltm:project init to seed; auto-replaced on change |
decision |
Architectural / key choices | Permanent — never trimmed |
progress |
Session log — what was done | UpdateContext hook at session end; trimmed to last 20 |
gotcha |
Warnings, pitfalls, blockers | Permanent — never trimmed |
What Happens at Session Start
The SessionStart hook:
- Resolves project from
registry.json - Regenerates
context-summary.mdfrom DB - Injects up to 60 lines of context into your session
- If DB has LTM memories: also injects importance-5 globals + top-15 project memories
You'll see ## Restored Project Context at session start when this fires. Acknowledge it briefly and confirm you're ready to continue.
LTM Commands (store and search learned insights)
| Command | When to use |
|---|---|
/openltm:memory learn |
After discovering a non-obvious pattern, gotcha, or decision |
/openltm:memory recall [query] |
Before starting work on a topic — surface past decisions |
/openltm:memory forget <id> |
When a memory is wrong or stale |
/openltm:memory relate <src> <tgt> <type> |
Link two related memories |
Recall before a non-trivial problem to check for prior knowledge; skip it for trivial one-liners.
What PreCompact Does
When compaction fires, PreCompact hook:
- Reads DB for all 4 context types for this project
- Writes
context-summary.md(max ~60 lines) as a human-readable fallback - This file is injected at the next
SessionStart
You do not manage context-summary.md — the hook overwrites it each compaction.
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 · 89 lines · 37 tokens per session scan A f0fd3d6f9f6d
session-context is a skill published in the GitHub repository RohiRIK/OpenLtm (26 stars, last pushed 25d ago), licensed MIT. It adds 37 tokens to every session and 989 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…