A memory and knowledge-base system that stores information as searchable connections between facts. It can save session memories or build a searchable knowledge base from documents such as PDFs.

It is for remembering project decisions, recalling past discoveries, and indexing document collections for later searches.

It helps recover useful information from earlier work instead of losing it in old conversations or scattered files.

grail — Skill for Codex by CAMARA-CHILENA-INTELIGENCIA-ARTIFICIAL

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/camara-chilena-inteligencia-artificial/cchia-skills/grail/github.svg)](https://agentmods.dev/skills/camara-chilena-inteligencia-artificial/cchia-skills/grail)

Your own site

<a href="https://agentmods.dev/skills/camara-chilena-inteligencia-artificial/cchia-skills/grail"><img src="https://agentmods.dev/badge/skills/camara-chilena-inteligencia-artificial/cchia-skills/grail/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/camara-chilena-inteligencia-artificial/cchia-skills/grail"><img src="https://agentmods.dev/badge/skills/camara-chilena-inteligencia-artificial/cchia-skills/grail.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 259 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,789 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00259	$0.02789
Opus 5	$0.00130	$0.01394
Sonnet 5	$0.00052	$0.00558
Haiku 4.5	$0.00026	$0.00279

Measured 12d ago against content hash 1b0dcfb43d16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

grail 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 12d ago.

The scan reads SKILL.md. This mod also ships 22 executable files (scripts/_common.py, scripts/append.py, scripts/delete.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/grail/SKILL.md · 257 lines

How it starts

The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GRAIL — knowledge graphs + agentic memory

GRAIL is a graph-RAG engine with two project modes that share one search engine:

Mode	Write path	Triggers
`memory`	tool-driven SDK writes under `./memories/` (no LLM at write time)	"remember that ...", "save this", "what did I learn last week"
`knowledge_base`	`grail index` over `./input/` (LLM extracts entities + relationships)	"index these PDFs", "build a KB from this corpus"

Both produce the same parquet artefacts, so every search mode (recall, local, cascade, global, document, agent) works on either kind of project.

Proactive behaviours (do these without being asked)

The user installed this skill on purpose. Treat that as standing consent to suggest memory + KB use. Be pushy but not annoying — one clear suggestion per save-worthy moment, accept "no" gracefully.

At the start of EVERY user message

Re-anchor on this skill. Do not assume context survives between turns.
If this is your first script call this session, run:
```
python scripts/session_start.py
```
It returns one JSON envelope with: (a) graphgrail install state + version, (b) every registered project with mode / path / entity + observation counts + pending proposals, (c) directive next_steps tailored to what it finds. CACHE the result for the rest of the session. Do not re-run setup.sh or list_grail_projects.py separately — they're subsumed by session_start.py. Only re-run session_start.py if you create or delete a project mid-session.
If setup.ok is false, run bash scripts/setup.sh first; then re-run session_start.py.
If zero projects exist AND this is a real conversation (not a one-shot question), propose creation:

"I notice you have GRAIL installed but no projects yet. Want me to set up a memory project so I can remember things across our sessions? It takes one command." Then if they agree (bare name → lands at ~/.grail/projects/<name>/):
```
python scripts/init_project.py --project my-memory --memory
```
After creating, re-run session_start.py so the cached state reflects the new project.

Read the full file on GitHub · 257 lines

Files

What ships with it

38 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

12d ago First seen · 257 lines · 259 tokens per session scan A 1b0dcfb43d16

Subscribe to this mod's changes

grail is a skill published in the GitHub repository CAMARA-CHILENA-INTELIGENCIA-ARTIFICIAL/cchia-skills (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 259 tokens to every session and 2,789 once invoked, about $0.0013 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.

Memory and context

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.

garrytan/gbrain · 52 tokens

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.…

mem0ai/mem0 · 273 tokens

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…

danielmiessler/LifeOS · 196 tokens

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.

opensquilla/opensquilla · 44 tokens

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…

shiwenwen/hope-agent · 115 tokens

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.

GanyuanRan/Aegis · 45 tokens