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 skills add runkids/feature-radar --skill feature-radar-validategit 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-validate)<a href="https://agentmods.dev/skills/runkids/feature-radar/feature-radar-validate"><img src="https://agentmods.dev/badge/skills/runkids/feature-radar/feature-radar-validate/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/skills/runkids/feature-radar/feature-radar-validate"><img src="https://agentmods.dev/badge/skills/runkids/feature-radar/feature-radar-validate.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 | $0.00127 | $0.00861 |
| Opus 5.5 | $0.00051 | $0.00344 |
| Sonnet 5.5 | $0.00025 | $0.00172 |
| Haiku 4.5 | $0.00013 | $0.00086 |
Grade A, and why
feature-radar-validate 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 27d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate Feature Radar
Run skills/feature-radar-validate/scripts/validate.sh from the project root to check SKILL.md frontmatter and .feature-radar/ SPEC compliance, then fix any issues found.
Why This Matters
The description field in SKILL.md has a 1024-character limit in the Agent Skills spec (agentskills.io/specification, checked 2026-09-29). Agents that enforce the spec may reject a longer description; Claude Code instead truncates the skill listing at 1,536 characters, cutting off trigger text. Similarly, .feature-radar/ files must follow SPEC.md naming and metadata conventions or downstream tools can't parse them. This skill catches these issues before they cause problems.
Workflow
Step 1: Run Validation
bash skills/feature-radar-validate/scripts/validate.sh
Read the full output. Note the exit code:
- Exit 0: all checks passed (may still have warnings)
- Exit 1: errors found — must be fixed
Step 2: Report Results
Present the results clearly:
── Feature Radar: Validate ──
Errors: {n}
Warnings: {n}
{List each error/warning with file path and issue}
If everything passes, say so and stop. No further action needed.
Step 3: Auto-Fix (if errors or warnings found)
For each issue, apply the appropriate fix:
| Issue | Fix Strategy |
|---|---|
description > 1024 chars |
Trim to fit — cut the least essential trigger phrases or examples first, keep the core "what it does" and "Use when" intact. Show before/after char count. |
description missing "Use when" |
Add a "Use when:" section based on the skill's purpose |
name not kebab-case |
Rename to kebab-case |
name missing |
Derive from directory name |
name > 64 chars |
Propose a shorter name and ask user to confirm — the name is how the skill is invoked |
name does not match directory |
Set name to the directory name; if the name is the intended one, ask user before renaming the directory (other skills reference it by path) |
| Body > 500 lines | Flag for user — this requires judgment about what to extract into reference files |
Filename not {nn}-{slug}.md |
Rename file to correct format |
Missing **Status**: / **Impact**: / **Effort**: |
Add field with a placeholder value, ask user to confirm |
base.md count mismatch |
Update the Tracking Summary table counts |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 27d ago Changed · -4 lines · -73 tokens per session 537ea97e5be9
- 1mo ago First seen · 84 lines · 200 tokens per session scan A 159312851774
feature-radar-validate is a skill published in the GitHub repository runkids/feature-radar (13 stars, last pushed 27d ago), licensed MIT. It adds 127 tokens to every session and 861 once invoked, about $0.0005 per session on Opus 5.5. 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
improve-code-quality
Guided journey from a working-but-untested vibe-coded prototype to a production-ready product with tests, clean structure, a business-rules boundary, and resilience at scale. Orchestrates nine skills phase by phase - working-with-legacy-code, clean-code, refactoring-patterns, software-design-philosophy…
working-with-legacy-code
Safely change and test untested codebases using Feathers' "Working Effectively with Legacy Code". Use when the user mentions "legacy code", "no tests", "untested codebase", "how do I test this", "seams", "characterization tests", "golden master", "sprout method", "afraid to change this code", "monster method"…
walk-forward-validation
The correct evaluation methodology for time-series sports prediction models. Use when user asks about model validation, cross-validation, train/test split, accuracy evaluation, overfitting detection, or statistical significance of sports model results. Refuses to run k-fold cross-validation on time-series data -…
write-tests
Write skillprobe YAML tests for LLM skills. Use when asked to write tests, create test scenarios, test a skill, generate skillprobe tests, or check whether a skill activates correctly.
ai-testing-safety
Find every way users can break your AI before they do. Use when you need to red-team your AI, test for jailbreaks, find prompt injection vulnerabilities, run adversarial testing, do a safety audit before launch, prove your AI is safe for compliance, stress-test guardrails, or verify your AI holds up against…
dspy-refine
Iterative self-improvement with dspy.Refine -- wraps any module, scores each attempt with a reward function, generates feedback on failures, and retries until a quality threshold is met. Use when you want outputs to improve through self-critique, need iterative revision of drafts, or want the LM to learn from its own…