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 commands/rohirik/openltm/onboardgit clone --depth 1 https://github.com/RohiRIK/OpenLtmWrote 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/commands/rohirik/openltm/onboard)<a href="https://agentmods.dev/commands/rohirik/openltm/onboard"><img src="https://agentmods.dev/badge/commands/rohirik/openltm/onboard.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 | $0.00031 | $0.00473 |
| Opus 5 | $0.00015 | $0.00236 |
| Sonnet 5 | $0.00006 | $0.00095 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
onboard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Runs the interactive 5-step terminal wizard for OpenLTM.
When to use
Run when starting a new project to seed goal, preferences, and context into LTM.
Safe to re-run — idempotent by default (skips if already onboarded; use --force to redo).
Usage
# Interactive (default)
bun run "${CLAUDE_PLUGIN_ROOT}/src/onboard.ts"
# Non-interactive (CI / scripted setup)
bun run "${CLAUDE_PLUGIN_ROOT}/src/onboard.ts" --non-interactive
# Force re-run even if already onboarded
bun run "${CLAUDE_PLUGIN_ROOT}/src/onboard.ts" --force
Steps
| # | Name | What happens |
|---|---|---|
| 1 | Diagnose | Checks env vars, DB access, hook wiring — aborts on CRITICAL |
| 2 | Register | Names the project; writes entry to registry.json |
| 3 | Goal | Captures current objective; saved to context_items + memories |
| 4 | Tour | Shows key commands (recall, learn, health, propose) |
| 5 | Done | Writes onboarded.flag to ${CLAUDE_PLUGIN_DATA}/ |
Flags
| Flag | Effect |
|---|---|
--non-interactive |
Skips all prompts; derives project name from cwd; uses default goal |
--force |
Ignores existing onboarded.flag and runs all steps again |
CRITICAL abort
If Step 1 finds CRITICAL issues (e.g. CLAUDE_PLUGIN_DATA not set, DB inaccessible), the wizard exits with code 1 and displays the failing checks. Fix these before continuing.
What it saves
registry.json— maps cwd to project namecontext_items—goalrow for the projectmemories— goal stored asarchitectureimportance-3 memoryonboarded.flag— timestamp file preventing duplicate runs
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.
- 4d ago First seen · 53 lines · 31 tokens per session scan A 15d958facba6
onboard is a command published in the GitHub repository RohiRIK/OpenLtm (26 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 473 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.