config

A command for viewing or changing Beacon’s settings, including its data providers, search thresholds, file chunking, indexing rules, and storage options. Changes are saved in a repository-local configuration file.

In plain words
What is it for?
Showing current settings, choosing an embedding provider, changing a setting, or resetting all or part of the configuration.
Why use it?
It keeps configuration changes in one place and shows which values are defaults and which have been overridden.

Command

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 commands/sagarmk/beacon-plugin/config
Clone the repo
git clone --depth 1 https://github.com/sagarmk/beacon-plugin
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 804 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00012 $0.00804
Opus 5 $0.00006 $0.00402
Sonnet 5 $0.00002 $0.00161
Haiku 4.5 $0.00001 $0.00080

Measured 2d ago against content hash 3d02d1c34bfe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

config 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 2d 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.

commands/config.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/config

Manage Beacon plugin configuration. All changes are saved to the repo-local .claude/beacon.json override file.

Routing

Parse $ARGUMENTS to determine the subcommand:

  • Empty or showShow
  • set <key> <value>Set
  • provider or provider <name>Provider
  • reset or reset <section>Reset

Show (default)

  1. Run: node ${CLAUDE_PLUGIN_ROOT}/scripts/config-manager.js show
  2. Format the JSON output as a readable config overview:
    • Show the active provider prominently at the top: Provider: ollama (local) or Provider: custom
    • Group settings by section: Embedding, Chunking, Indexing, Search, Storage
    • For each setting, show the key, value, and mark [override] if source is "user" — leave unmarked if default
    • For array values (include/exclude patterns), show as a compact comma-separated list
    • At the bottom, list available providers: Available: ollama, openai, voyage, litellm
    • Keep total output under 30 lines

Set

  1. Run: node ${CLAUDE_PLUGIN_ROOT}/scripts/config-manager.js set <key> <value>
  2. If the script exits with an error (JSON on stderr), show the error message. If it's an unknown key, show the list of valid keys.
  3. If dimensions_changed is true in the output:
    • ⚠️ Warn: "Changing dimensions from <old> to <new> makes existing embeddings incompatible."
    • Ask: "Run /reindex now to rebuild the index?"
    • If the user confirms, delete the DB file (rm -f .claude/.beacon/embeddings.db) and run node ${CLAUDE_PLUGIN_ROOT}/scripts/sync.js
  4. Otherwise, confirm: Set search.similarity_threshold → 0.5

Provider

  1. Run: node ${CLAUDE_PLUGIN_ROOT}/scripts/config-manager.js provider <name>
  2. If no name given, the script lists available providers — format them as a table with name, description, model, and dimensions.
  3. If the provider is not found, show the error with available provider names.
  4. If successful, show what was applied: model, endpoint, dimensions.
  5. If api_key_env is not empty/none, remind: "Make sure OPENAI_API_KEY is set in your environment."
  6. If dimensions_changed is true:
    • ⚠️ Warn: "Switching from <old> to <new> dimensions. Existing embeddings are incompatible."
    • Ask: "Run /reindex now to rebuild the index with the new provider?"
    • If the user confirms, delete the DB and run sync.

Read the full file on GitHub · 68 lines

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. 2d ago First seen · 68 lines · 12 tokens per session scan A 3d02d1c34bfe

Subscribe to this mod's changes

config is a command published in the GitHub repository sagarmk/beacon-plugin (43 stars, last pushed 12d ago), licensed MIT. It adds 12 tokens to every session and 804 once invoked, about $0.0001 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 2026-08-30.