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 the-essential/reliquery --skill cartographgit clone --depth 1 https://github.com/the-essential/reliqueryWrote 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/the-essential/reliquery/cartograph)<a href="https://agentmods.dev/skills/the-essential/reliquery/cartograph"><img src="https://agentmods.dev/badge/skills/the-essential/reliquery/cartograph/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/the-essential/reliquery/cartograph"><img src="https://agentmods.dev/badge/skills/the-essential/reliquery/cartograph.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 | $0.00198 | $0.02109 |
| Opus 5 | $0.00099 | $0.01055 |
| Sonnet 5 | $0.00040 | $0.00422 |
| Haiku 4.5 | $0.00020 | $0.00211 |
Grade A, and why
cartograph 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 10d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
Cartograph is the relational mapping layer of Reliquery. Where memorize indexes relic content into searchable drawers, cartograph indexes relic relationships into queryable graph triples. The two are complementary — drawers give Claude prose and flavor, the KG gives Claude structured facts and temporal state. Together they form the complete memory of a world: what things are and how they connect.
Cartograph approaches the knowledge graph the way a cartographer approaches unmapped territory — survey first, chart second, verify third. Every triple it proposes has been cross-referenced against vault content. Every triple it files has been reviewed by the user. The KG is the authoritative record of what is currently true in a world; carelessness here means Claude acts on bad facts in future sessions.
When to Use Cartograph vs. Other Skills
| Situation | Skill |
|---|---|
| Raw content → structured relics | Chronicle |
| Relics → searchable drawers | Memorize |
| Entity relationships → KG triples | Cartograph |
| Palace drawers need to be deleted | Forget |
| Full pipeline: content → relics → memory → KG | Study |
Phase 1 — Survey
Search the vault for everything relevant to the target entity. Build a complete picture before designing any triples.
How to search:
- Direct name search:
mempalace_search(query="[entity]", wing="[wing]", limit=10) - Temporal history:
mempalace_kg_timeline(entity="[entity]")— review the entity's existing relationship timeline before proposing new triples. This prevents duplicates, reveals invalidated facts that shouldn't be re-added, and surfaces temporal gaps worth filling. - Follow the threads — every connected entity in the results gets a follow-up search
- Relationship-specific queries:
"[entity] [connected entity] relationship","[entity] motivations goals" - Typical scope: 3–6 searches for a single character, 5–10 for a major arc or faction
What to extract:
- Named relationships (allies, enemies, handlers, mentors, family)
- Organizational affiliations (factions, roles, departments)
- Status facts (alive, dead, missing, transformed)
- Identity links (aliases, codenames, true identities)
- Temporal markers (when relationships started, ended, changed)
- Narrative state (what's happening now, what's unresolved)
- Mystery flags (unknown connections, foreshadowing, unrevealed links)
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.
- 10d ago First seen · 194 lines · 198 tokens per session scan A 3dac5bb9f146
cartograph is a skill published in the GitHub repository the-essential/reliquery (5 stars, last pushed 3mo ago), licensed MIT. It adds 198 tokens to every session and 2,109 once invoked, about $0.0010 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
weekly-digests
Generate a serial week-by-week narrative digest of a project's full claude-mem timeline. Splits the timeline into per-ISO-week files, then runs one consecutive subagent per week — each receiving the prior week's carry-forward block — to produce one chapter per ISO week of data. Use when asked for "weekly digests"…
cloud-sync
Set up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.
hivemind-memory
Global team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling information.
init
Install or update OwnMem in the current repository. Use when the user asks to set up OwnMem, add local project memory for coding agents, or refresh an existing OwnMem installation after a version bump.
mnemo-cortex
Installs and wires Mnemo Cortex (local-first persistent memory) into OpenClaw and other MCP-capable agents. Use for cross-session recall, decision history, or multi-agent shared memory.
honcho-integration
Integrate Honcho memory into existing Python or TypeScript codebases. Use when adding Honcho SDK, setting up peers, configuring sessions, and accessing Honcho's representation.