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.
npx agentmods add skills/runkids/feature-radar/feature-radar-refnpx skills add runkids/feature-radar --skill feature-radar-refgit clone --depth 1 https://github.com/runkids/feature-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/skills/runkids/feature-radar/feature-radar-ref)<a href="https://agentmods.dev/skills/runkids/feature-radar/feature-radar-ref"><img src="https://agentmods.dev/badge/skills/runkids/feature-radar/feature-radar-ref.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 | $0.00199 | $0.00856 |
| Opus 5 | $0.00100 | $0.00428 |
| Sonnet 5 | $0.00040 | $0.00171 |
| Haiku 4.5 | $0.00020 | $0.00086 |
Grade A, and why
feature-radar-ref 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 6d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Add Reference
Record external observations into .feature-radar/references/.
Deep Read
Behavioral Directives
Workflow
- Identify the source — ask the user what they observed:
- Interesting project, technique, or creative approach?
- Ecosystem trend or emerging pattern?
- Notable feature or solution from a related project?
- User comparison, feedback, or question?
- Research, article, or talk with relevant insights?
- Gather context — URL, date, key details. If the user provides a GitHub URL, fetch the issue/PR for full context.
- Classify — determine the right file:
- Existing reference file → append a new entry
- New topic → create
.feature-radar/references/{topic}.md
- Assess impact:
File Format
Use the format defined in ../feature-radar/references/SPEC.md § 3.5 (references/{topic}.md).
Naming Convention
Name by the subject being tracked, not the event:
- Good:
vercel-skills-ecosystem.md,agent-path-conventions.md,cli-ux-patterns.md - Bad:
2026-02-18-update.md,interesting-finding.md
Guidelines
- Always cite source URLs and dates for traceability.
- Append new entries chronologically to existing files — don't create a new file per observation.
- Be objective. Record what happened, then assess implications separately.
- If the observation reveals an unmet need or innovation opportunity, proactively suggest creating an opportunity.
- Look for creative inspiration, not just feature gaps — how others solve problems can spark new ideas.
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.
- 6d ago First seen · 88 lines · 199 tokens per session scan A e3a15f868c08
feature-radar-ref is a skill published in the GitHub repository runkids/feature-radar (13 stars, last pushed 6mo ago), licensed MIT. It adds 199 tokens to every session and 856 once invoked, about $0.0010 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.
Other skills, from other repositories
cre-asset-management
CRE Asset Management analysis suite — 9 specialist skills for post-acquisition multifamily operations including annual budgeting, monthly variance analysis, rent collection, renewal decisions, lease-up tracking, capex execution, NOI improvement, hold/sell/refi scenario analysis, and quarterly asset review memos.
cre-brokerage
CRE Brokerage Investment Sales v1 - 8 specialist skills for U.S. seller-side commercial investment sales brokers, covering assignment intake, broker opinion of value, listing proposal, OM and teaser drafting, buyer process management, bid leveling, negotiation support, and PSA-to-close coordination.
cre-capital-markets
CRE Capital Markets and Debt Maturity suite - 8 specialist skills for maturity diagnostics, refinance proceeds gaps, extensions, workouts, rescue capital, term sheet comparison, CMBS special servicing readiness, lender updates, and recap IC memos.
cre-due-diligence
CRE Due Diligence analysis suite — 7 specialist skills for multifamily property analysis including rent roll validation, expense benchmarking, market study, physical inspection, environmental review, title review, and tenant credit assessment.
cre-legal
CRE Legal review suite — 6 specialist skills for PSA review, title & survey analysis, estoppel tracking, loan document review, insurance coordination, and transfer document preparation for multifamily acquisitions.
cre-office
CRE Office analysis suite - 8 specialist skills for U.S. office acquisitions, refinancings, lease-up, tenant credit, TI/LC underwriting, financing fit, and investment committee memo writing.