propose-competitors

propose-competitors is a command for Claude Code from Stahl-G/briefloop. It costs 12 tokens per session (290 once invoked), scanned A, original, MIT.

A command that recommends possible competitors for a workspace using the workspace’s company, industry, market, and existing competitor information. It saves suggestions for review without approving or merging them.

In plain words
What is it for?
Use it to create or update a competitor-candidates file, including each candidate’s relationship, overlap, reason for inclusion, and confidence, before manually approving confirmed entries.
Why use it?
It provides a structured starting list while keeping the final decision with a person. This avoids treating unverified suggestions as confirmed competitors.

Command for Claude Code

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/stahl-g/briefloop/propose-competitors
Clone the repo
git clone --depth 1 https://github.com/Stahl-G/briefloop

Made for: Claude Code.

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.

agentmods badge for propose-competitors

README.md
[![agentmods](https://agentmods.dev/badge/commands/stahl-g/briefloop/propose-competitors.svg)](https://agentmods.dev/commands/stahl-g/briefloop/propose-competitors)
Your own site
<a href="https://agentmods.dev/commands/stahl-g/briefloop/propose-competitors"><img src="https://agentmods.dev/badge/commands/stahl-g/briefloop/propose-competitors.svg" alt="Measured on agentmods" height="20"></a>
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 290 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 $0.00290
Opus 5 $0.00006 $0.00145
Sonnet 5 $0.00002 $0.00058
Haiku 4.5 $0.00001 $0.00029

Measured 4d ago against content hash c4b9fbe32303, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

propose-competitors 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 4d 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/commands/propose-competitors.md · 33 lines

What it actually says

You are recommending competitor candidates for workspace: $ARGUMENTS

Follow this sequence:

  1. Read context files:

    • $ARGUMENTS/user.md
    • $ARGUMENTS/config.yaml
    • $ARGUMENTS/competitor_universe.yaml (target entity and any existing entities)
  2. Call the market-competitor-planner subagent:

    • Provide user.md context (company, industry, market_scope, focus_areas).
    • Ask it to recommend 3-8 competitor entities.
    • Each candidate must include: entity_id, name, aliases, relation, relevance_reason, market_overlap (geography, product, value_chain), confidence, and approved: false.
  3. Write $ARGUMENTS/competitor_candidates.yaml:

    • Merge existing approved-but-not-merged candidates (if any).
    • Add new recommendations from the planner.
    • Do NOT set approved: true for any candidate.
  4. Report:

    • How many candidates were added.
    • Which entities were recommended and why (briefly).
    • Remind user to review candidates, set approved: true on confirmed ones, then run briefloop competitors merge --config $ARGUMENTS/config.yaml.
    • Do not auto-approve or merge candidates.
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. 4d ago First seen · 33 lines · 12 tokens per session scan A c4b9fbe32303

Subscribe to this mod's changes

propose-competitors is a command published in the GitHub repository Stahl-G/briefloop (9 stars, last pushed 6d ago), licensed MIT. It adds 12 tokens to every session and 290 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 2026-08-31.