agentmods.dev

dakera-cli CLAUDE.md

Project instructions for Dakera CLI, a Rust command-line program for managing memories, sessions, agents, keys, namespaces, and vector search through the Dakera platform.

In plain words
What is it for?
Building, testing, formatting, linting, and extending Dakera CLI commands that communicate with Dakera services.
Why use it?
They explain the command structure, configuration sources, output formats, and project layout so changes follow the CLI and its REST API consistently.

Instructions file

8 17d ago A scan 282 tokens original MIT
View the source file Dakera-AI/dakera-cli
Install

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.

agentmods
npx agentmods add instructions/dakera-ai/dakera-cli/claude-md
Clone the repo
git clone --depth 1 https://github.com/Dakera-AI/dakera-cli
Per session 282 This file is loaded in full into every session.
When invoked 282 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00282 $0.00282
Opus 5 $0.00141 $0.00141
Sonnet 5 $0.00056 $0.00056
Haiku 4.5 $0.00028 $0.00028

Measured 3d ago against content hash 4869369eeee5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dakera-cli CLAUDE.md 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.

CLAUDE.md · 28 lines

What it actually says

dakera-cli

Rust CLI for the Dakera AI memory platform — manage memories, sessions, agents, namespaces, keys, and vector search from the command line.

Key Commands

cargo build --release        # Build CLI binary → target/release/dakera-cli
cargo test                   # Run tests
cargo clippy                 # Lint
cargo fmt                    # Format
./target/release/dakera-cli --help   # Show all subcommands

Architecture

  • src/main.rs — CLI entry; clap command routing
  • src/commands/ — One module per subcommand: memory, session, agent, keys, knowledge, vector, namespace, admin, health, ops, analytics, completion, init, config, index
  • src/config.rs — Reads ~/.dakera/config.toml (API base URL + auth token)
  • src/output.rs — Table / JSON / pretty-print output formatters
  • src/error.rs — Error types wrapping API responses

Conventions

  • Commands map 1-to-1 to dakera REST API endpoints
  • Default output: human-readable table; --json flag for machine-parseable output
  • Config precedence: env vars > CLI flags > ~/.dakera/config.toml
  • Releases published alongside the dakera server (same version tag)
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.

  1. 3d ago First seen · 28 lines · 282 tokens per session scan A 4869369eeee5

Subscribe to this mod's changes

dakera-cli CLAUDE.md is an instructions file published in the GitHub repository Dakera-AI/dakera-cli (8 stars, last pushed 17d ago), licensed MIT. It adds 282 tokens to every session, about $0.0014 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.

LanguagesMemory and contextRustagent-memoryai-memoryclicommand-lineknowledge-graphmemory-server
Related

Other instructions, from other repositories

dakera-rs CLAUDE.md

Claude Code instructions for Dakera-AI/dakera-rs, covering dakera-rs, key commands, architecture and conventions.

Dakera-AI/dakera-rs · 280 tokens

shodh-memory CLAUDE.md

Instructions for varun29ankuS/shodh-memory, covering shodh-memory project instructions, must rules, code standards, persistent memory (shodh-memory mcp) and codebase map.

varun29ankuS/shodh-memory · 532 tokens

vellis AGENTS.md

Instructions for volantlabs/vellis, covering agents.md, repository purpose, startup checks, installing vellis for a user and model-first component workflow.

volantlabs/vellis · 4,953 tokens

pos CLAUDE.md

Instructions for xcota/pos, covering personal os, rules, memory, budget and hard rules.

xcota/pos · 899 tokens

pos AGENTS.md

Instructions for xcota/pos, covering agents.md — workspace boot rules, session boot, memory, safety and language.

xcota/pos · 629 tokens

cli AGENTS.md

Instructions for konteks/cli, covering agent instructions, project overview, tech stack, repository layout and common commands.

konteks/cli · 1,050 tokens