radar-plan-targets
Skill4 starsChanged 5 months agoMITView on GitHub
Builds the per-competitor scout job list for a radar gather run. Reads radar.config.json, enforces the cap of 8 competitors and waves of 8, and emits one ready-to-spawn job spec per competitor (competitor, keywords, geo, scout depth, brightdata prefix, output path). Use as the first step of /radar, before spawning competitor-scout subagents.
In this repository8 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- radar-diff-changesSkill
- radar-merge-briefingSkill
- radar-onboardSkill
- radar-provision-notionSkill
- radar-publish-councilSkill
- radar-publish-notionSkill
- radar-render-dashboardSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
Read radar.config.json. If missing or missing a verified brightdata_prefix, stop and route the user to /radar-setup.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
radar-plan-targets
Automation level: AUTONOMOUS. This is read-and-plan only; it spawns nothing.
Goal: turn the config into a clean list of scout jobs the /radar command will fan out in one
message. See cost-control.md for the caps.
Steps
- Read
radar.config.json. If missing or missing a verifiedbrightdata_prefix, stop and route the user to/radar-setup. - Establish the run id and output directory: a date-stamped run, for example
outputs/dossiers/<YYYY-MM-DD>/. Create the directory. Each scout writes one file<competitor-slug>.jsonthere. - Apply caps: take at most the first 8 competitors. If more were configured, note which were skipped. Plan waves of at most 8 (normally one wave given the cap).
- For each competitor, build a job spec the scout understands:
COMPETITOR: name + domainMY_KEYWORDS: from configGEO: config geoSCOUT_DEPTH: the three flags from configBRIGHTDATA_PREFIX: the verified prefix from configOUTPUT_PATH:outputs/dossiers/<run-date>/<slug>.jsonFRESHNESS: the news/funding/sentiment day windows (config overrides or the defaults in freshness.md)
- Return the job list and the run directory to the caller. Do not gather anything yourself.
Edge cases
- Zero competitors configured: stop and tell the user to add competitors via
radar-onboard. - Duplicate domains: dedupe, keep the first.
- A competitor missing a domain: keep the name, let the scout resolve the domain via search; mark it so the scout knows to confirm the domain first.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

