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.
git clone --depth 1 https://github.com/sabahudin-web/competitive-intelligence-radarWrote 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/commands/sabahudin-web/competitive-intelligence-radar/radar-council)<a href="https://agentmods.dev/commands/sabahudin-web/competitive-intelligence-radar/radar-council"><img src="https://agentmods.dev/badge/commands/sabahudin-web/competitive-intelligence-radar/radar-council/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/commands/sabahudin-web/competitive-intelligence-radar/radar-council"><img src="https://agentmods.dev/badge/commands/sabahudin-web/competitive-intelligence-radar/radar-council.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 | $0.00073 | $0.00793 |
| Opus 5 | $0.00036 | $0.00396 |
| Sonnet 5 | $0.00015 | $0.00159 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade A, and why
radar-council 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/radar-council
You are the team LEAD. This command is CHECKPOINT: it is token heavy because each teammate is a separate Claude instance. You use a real AGENT TEAM here, never plain subagents, because the analysts must see and challenge each other. See subagents-vs-agent-teams.md and agent-teams-setup.md.
Preconditions
- A briefing exists for the latest run (
radar.config.jsonlast_run.briefing_path). If not, stop and tell the user to run/radarfirst. - Agent teams are enabled: Claude Code v2.1.32+ and
CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1. If not, show the fix from the setup reference and stop. - The user's own BrightData and Notion MCP are connected (teammates load MCP from USER settings, not
plugin frontmatter). The verified prefixes are in the config; if they are stale, suggest re-running
/radar-setup.
CHECKPOINT
Tell the user plainly: the council spawns 4 Sonnet teammates that debate, which uses significantly more tokens than a normal run. Ask for an explicit yes before spawning. Do not proceed on silence.
Sequence
-
Create ONE agent team and spawn 4 teammates BY NAME from this plugin's agent definitions:
pricing-analyst,product-gap-analyst,threat-sentiment-analyst,devils-advocate. Give each a spawn prompt that includes: the absolute path to the latest briefing markdown and the combined dossier JSON, the live BrightData prefix for light spot-checks, its specific lens, and the instruction to message and challenge the other teammates. -
Run the debate. Have the analysts post opening reads, then actively challenge each other (the devil's advocate tries to disprove the others; each defends with cited evidence or concedes). Steer toward convergence; tell teammates to wait for each other rather than racing ahead. Keep it to a focused debate, not an endless one.
-
Synthesize the Strategic War Room addendum yourself as lead: a short consensus summary, the top recommended moves (each with a one-line rationale and the supporting source or dossier field), and a dissents-and-risks list for anything still disputed. No fabrication, no em or en dashes.
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.
- 11d ago First seen · 59 lines · 73 tokens per session scan A 1d0a4ffae939
radar-council is a command published in the GitHub repository sabahudin-web/competitive-intelligence-radar (3 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 793 once invoked, about $0.0004 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.
Other commands, from other repositories
status
Show current research session state and progress.
resume
Resume a previous research session from progress file.
init
Manually initialize or reload research context for sigint.
falsify
Adversarially falsify research findings via web-only disconfirming search; quarantine, downgrade, or annotate findings based on verdicts.
augment
Deep-dive into a specific area of current research.
issues
Create GitHub issues from research findings as atomic deliverables.