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 skills add WilliamJnsson/NarratorDB --skill onboardgit clone --depth 1 https://github.com/WilliamJnsson/NarratorDBWrote 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/skills/williamjnsson/narratordb/onboard)<a href="https://agentmods.dev/skills/williamjnsson/narratordb/onboard"><img src="https://agentmods.dev/badge/skills/williamjnsson/narratordb/onboard/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/skills/williamjnsson/narratordb/onboard"><img src="https://agentmods.dev/badge/skills/williamjnsson/narratordb/onboard.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 | $0.00039 | $0.00648 |
| Opus 5 | $0.00019 | $0.00324 |
| Sonnet 5 | $0.00008 | $0.00130 |
| Haiku 4.5 | $0.00004 | $0.00065 |
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 11d 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
Onboard NarratorDB
Perform one quiet, read-only readiness check:
- Send one short progress update:
Checking NarratorDB for this project… - Call
statusexactly once withscope="project"andfull_check=false. - Interpret the structured response internally. Read the current-project count
from
memory_counts.current_workspaceand the user's all-workspace count frommemory_counts.current_user_total. Do not echo raw JSON. Read the automatic policy fromcapture_policy. - Inspect
scope_diagnostics.project_writes_blockedbefore calling the project ready. If it is true, finish with one warning and stop:NarratorDB is healthy, but project memory is not ready — Codex started outside a safe project scope. Start Codex from the intended project folder and run onboarding again. (<current> current-workspace memories; <total> across your workspaces.) - Otherwise finish with one compact result:
- ready in Private mode:
NarratorDB is ready — Private mode, <policy> capture, local recall, <current> current-workspace memories (<total> across your workspaces). - ready in Intelligence mode:
NarratorDB is ready — Intelligence mode, <policy> capture, local recall, <current> current-workspace memories (<total> across your workspaces). - path-derived but writable: append one short form of
scope_warning; do not claim the scope is portable across machines. - degraded:
NarratorDB is degraded: <short reason>. <one recovery action>. - unavailable:
NarratorDB is unavailable. Install or verify uvx, then restart Codex.
- ready in Private mode:
Do not call resume, recall, or remember during routine onboarding. The
SessionStart hook handles normal context loading; explicit resume and write
requests are separate interactions. Do not list database paths, user IDs,
workspace IDs, health objects, or timing fields unless the user asks for
diagnostics. Never say that the database is empty merely because
memory_counts.current_workspace is zero; report current-workspace and
all-workspace counts separately.
Private mode needs no account, API key, or external model. An existing Intelligence database remains Intelligence, but its recall is still local. Do not install unrelated packages, change mode, request a provider key, or expose environment contents. Codex controls native status/spinner animation; this skill can provide concise commentary but cannot customize that animation.
Policy meanings: manual saves only explicit remember calls; preferences
also learns high-confidence personal preferences and routines from the current
prompt; sessions additionally captures bounded project conversations. Never
describe Preferences as arbitrary AI extraction. If the user wants to change
mode or policy, use the setup skill rather than mutating configuration during
a readiness check.
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.
- 11d ago First seen · 47 lines · 39 tokens per session scan A 63412461db31
onboard is a skill published in the GitHub repository WilliamJnsson/NarratorDB (0 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 648 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 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.