Borrowing it
Nothing to install: this file belongs to Lyzr-Cognis/claude-cognis. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Lyzr-Cognis/claude-cognis/main/.agents/skills/cognis-skills/SKILL.mdgit clone --depth 1 https://github.com/Lyzr-Cognis/claude-cognisWrote 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/lyzr-cognis/claude-cognis/cognis-skills)<a href="https://agentmods.dev/skills/lyzr-cognis/claude-cognis/cognis-skills"><img src="https://agentmods.dev/badge/skills/lyzr-cognis/claude-cognis/cognis-skills/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/lyzr-cognis/claude-cognis/cognis-skills"><img src="https://agentmods.dev/badge/skills/lyzr-cognis/claude-cognis/cognis-skills.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 | $0.00107 | $0.01004 |
| Opus 5 | $0.00053 | $0.00502 |
| Sonnet 5 | $0.00021 | $0.00201 |
| Haiku 4.5 | $0.00011 | $0.00100 |
Grade A, and why
cognis-skills scanned grade A with 1 finding 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.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
compatibility: Requires curl and LYZR_API_KEY environment variable (get key at studio.lyzr.ai). Internet access to memory.studio.lyzr.ai. Copies of this mod
1 near-identical copy found in the catalogue:
- cognis — 97% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cognis — Persistent Memory for AI Agents
Cognis gives you long-term memory that persists across sessions. Memories are scoped per-user and per-project, with optional team-wide sharing.
Setup
The LYZR_API_KEY environment variable must be set. Get a key at studio.lyzr.ai.
export LYZR_API_KEY="your-key-here"
Optionally set COGNIS_OWNER_ID to override the default owner (system username).
Scoping
Cognis uses two levels of scoping to keep memories organized:
- owner_id: Identifies the user. Defaults to the system username (
whoami). Override withCOGNIS_OWNER_ID. - agent_id: Identifies the project context.
- Personal scope:
claudecode_<sha256(git_root)[:16]>— unique per user per project. - Team scope:
repo_<sanitized_repo_name>— shared across all contributors to a repo.
- Personal scope:
The scripts detect the git root and remote automatically. No manual configuration needed.
Saving Memories
Save something the user wants to remember:
bash scripts/cognis-save.sh "The user prefers PostgreSQL for all new services"
Save a team-wide memory (visible to all repo contributors):
bash scripts/cognis-save.sh "Deploy process: run migrations first, then deploy API, then workers" --team
Read references/api-reference.md for full parameter details.
Searching Memories
Search for relevant memories:
bash scripts/cognis-search.sh "what database do we use"
Search only team memories:
bash scripts/cognis-search.sh "deployment process" --repo
Search both personal and team:
bash scripts/cognis-search.sh "auth setup" --both
Getting Assembled Context
Fetch relevant context (combines short-term and long-term memory):
bash scripts/cognis-context.sh
This returns assembled context for the current project, including relevant personal and team memories.
When to Use Personal vs Team Scope
- Personal (default): User preferences, individual notes, personal workflow details, things the user says about themselves.
- Team (
--team): Architecture decisions, deployment processes, coding conventions, shared knowledge that any contributor would benefit from.
What ships with it
10 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.
- LICENSE 1.0 KB
- README.md 2.1 KB
- references/api-reference.md 4.9 KB
- references/architecture.md 2.7 KB
- references/quickstart.md 1.5 KB
- references/sdk-guide.md 2.4 KB
- references/use-cases.md 2.5 KB
- scripts/cognis-context.sh 3.3 KB runs code
- scripts/cognis-save.sh 3.4 KB runs code
- scripts/cognis-search.sh 3.9 KB runs code
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 · 114 lines · 107 tokens per session scan A 04b10cceb95e
cognis-skills is a skill published in the GitHub repository Lyzr-Cognis/claude-cognis (20 stars, last pushed 5mo ago), licensed MIT. It adds 107 tokens to every session and 1,004 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.