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)<a href="https://agentmods.dev/commands/sabahudin-web/competitive-intelligence-radar/radar"><img src="https://agentmods.dev/badge/commands/sabahudin-web/competitive-intelligence-radar/radar.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.00627 |
| Opus 5 | $0.00034 | $0.00313 |
| Sonnet 5 | $0.00013 | $0.00125 |
| Haiku 4.5 | $0.00007 | $0.00063 |
Grade A, and why
radar 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 8d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/radar
You are the gather orchestrator. This run is AUTONOMOUS end to end. You use SUBAGENTS for gathering, never an agent team, because scouts work independently and only report back. See subagents-vs-agent-teams.md.
Precondition: radar.config.json exists with verified MCP prefixes. If not, stop and tell the user
to run /radar-setup.
Sequence
-
Run the
radar-plan-targetsskill to read the config, enforce the cap of 8 and waves of 8, create the run dossier directory, and produce one scout job spec per competitor. -
Fan out the scouts. Spawn one
competitor-scoutsubagent PER competitor, all in ONE message (multiple tool calls in a single response) so they run in parallel. Give each scout its job spec from step 1: the competitor, my keywords, geo, scout depth flags, the live BrightData prefix, the freshness windows, and its uniqueOUTPUT_PATH. Scouts gather with BrightData, write one cited JSON dossier each, and report back. They never message each other. If there are more than 8 competitors (there should not be after the cap), run a second wave after the first returns. -
Run the
radar-diff-changesskill to compare this run's dossiers against last run and produce a ranked, freshness-aware change set. -
Run the
radar-merge-briefingskill to write the three local artifacts: briefing markdown, the combined raw dossier JSON, and the dashboard data JSON. Every claim carries a source URL. -
Run the
radar-publish-notionskill to upsert the Competitors rows (with the Change field) and create the Briefings page. If Notion is not provisioned, note it and continue; the local and dashboard surfaces still publish. -
Run the
radar-render-dashboardskill to inject the data into the self-contained HTML dashboard. -
Print the THREE output locations clearly:
- Local briefing markdown path and combined dossier JSON path.
- Notion briefing page link (or a note that Notion was skipped).
- Local dashboard HTML path (offer to open it).
Then hint: "Run
/radar-councilto convene the strategic war room over this briefing."
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.
- 8d ago First seen · 48 lines · 67 tokens per session scan A 27ffc309e467
radar is a command published in the GitHub repository sabahudin-web/competitive-intelligence-radar (3 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 627 once invoked, about $0.0003 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.