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/the-essential/reliquery/studynpx skills add the-essential/reliquery --skill studygit clone --depth 1 https://github.com/the-essential/reliqueryWhat 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 | $0.00155 | $0.02009 |
| Opus 5 | $0.00077 | $0.01005 |
| Sonnet 5 | $0.00031 | $0.00402 |
| Haiku 4.5 | $0.00015 | $0.00201 |
Grade A, and why
study 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
Study is the orchestrator — the master pipeline that chains chronicle, memorize, cartograph, and forget into a single coherent operation. Where the individual skills each handle one stage of the Reliquery lifecycle, study handles the intent: "I have content, and I want the system to learn it."
Study's disposition is efficiency without shortcuts. It moves through the pipeline briskly, collapsing unnecessary pauses between stages while preserving every checkpoint that protects the user's world. It recognizes when a step can be skipped (no new relics to index, KG already up to date) and says so rather than running empty phases. It recognizes when a step needs to be added (stale drawers that should be forgotten before re-indexing) and offers it seamlessly.
The user should never have to think about which skill to invoke or in what order. Study handles the routing.
How Study Works
Study operates in three stages that map to the underlying skills, with decision points between them that determine whether to continue, branch, or stop.
Content → [Chronicle] → Relics → [Memorize] → Drawers → [Cartograph offer] → KG
↑
[Forget if needed]
The user provides content and an intent. Study figures out the rest.
Stage 1 — Intake & Memory Check
Before invoking chronicle, study performs its own reconnaissance to understand what the system already knows and what's actually new.
1a — Load the palace
Call mempalace_status to confirm the system is live and identify the relevant wing.
1b — Scan the input
Read the user's provided content (manuscript excerpt, session log, conversation, scene draft) and identify every named entity: characters, factions, locations, systems, events.
1c — Memory check
For each identified entity, run dual lookups in parallel:
mempalace_search(query="[entity]", wing="[wing]")— what drawers existmempalace_kg_query(entity="[entity]")— what the KG knows
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 · 159 lines · 155 tokens per session scan A 3e41b9899734
study is a skill published in the GitHub repository the-essential/reliquery (5 stars, last pushed 3mo ago), licensed MIT. It adds 155 tokens to every session and 2,009 once invoked, about $0.0008 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
dialogue-gym
A dialogue coach that teaches dialogue craft framed by the writer's stated intent and level, sets a targeted drill, has the writer write it, then evaluates and ranks the attempt against dialogue criteria and assigns the next drill. Use it when a writer wants to deliberately improve dialogue — subtext, beats, distinct…
prose-rhythm
A prose-rhythm coach that teaches sentence variety, sound, and cadence framed by the writer's intent and level, sets a drill, has the writer write it, then scores and ranks the attempt against rhythm criteria and assigns the next drill. Use it when a writer wants to tune the music of their prose — sentence length…
psychic-distance
A POV-craft coach that teaches the five rungs of psychic distance framed by the writer's intent and level, sets a drill, has the writer write it, then evaluates and ranks how well they controlled the distance and assigns the next drill. Use it when a writer wants to master narrative distance — sliding from…
scene-architecture
A scene-craft coach that teaches scene structure (goal, conflict, disaster; scene and sequel) framed by the writer's intent and level, sets a laddered drill, has the writer write it, then scores and ranks the attempt against scene criteria and assigns the next drill. Use it when a writer wants to deliberately…
agent-first-pages
Simulates a literary agent reading a manuscript's opening pages cold from the slush pile and delivering the verdict — request more, or pass — with the honest reasoning behind it. Use it when a writer is preparing to query and wants to know how their opening reads to a gatekeeper skimming fast. It reads and judges; it…
beta-reader-panel
Simulates a panel of distinct beta-reader personas reacting to a manuscript chapter by chapter — where they're confused, bored, delighted, or lost. Use it when a writer wants a reader's-eye reaction to a draft before recruiting real beta readers, or between drafts to find the places the story isn't landing. It reacts…