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/sliday/harn/car-analyzernpx skills add sliday/harn --skill car-analyzergit clone --depth 1 https://github.com/sliday/harnWrote 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/sliday/harn/car-analyzer)<a href="https://agentmods.dev/skills/sliday/harn/car-analyzer"><img src="https://agentmods.dev/badge/skills/sliday/harn/car-analyzer.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 | $0.00042 | $0.00495 |
| Opus 5 | $0.00021 | $0.00247 |
| Sonnet 5 | $0.00008 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade A, and why
car-analyzer 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 3d 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.
What it actually says
Reference: https://harn.app/kb/evals.html — "Deterministic verifiers over LLM-as-judge"
CAR Framework Analyzer
Audit the current project against the three layers of a robust harness.
CAR Scorecard (check each item, tally points)
Control Layer (40 points)
- AGENTS.md or CLAUDE.md exists and < 100 lines (10 pts)
- Type checker configured and runs without errors (10 pts)
- Linter configured (eslint/clippy/ruff/golangci-lint) (5 pts)
- Test directory exists with actual test files (10 pts)
- Architectural constraints documented in AGENTS.md (5 pts)
Agency Layer (25 points)
- PreToolUse security guard hook active (10 pts)
- Tool permissions explicitly scoped (5 pts)
- Sub-agent delegation patterns documented (5 pts)
- File write boundaries defined (5 pts)
Runtime Layer (35 points)
- Stop hook (quality gate) active and verified (15 pts)
- PostToolUse hooks configured (formatter and/or trace) (5 pts)
- Infinite-loop prevention in Stop hook verified (10 pts)
- Session recovery artifacts exist (CHECKPOINT.json or LEARNED.md) (5 pts)
Scoring
- 80-100: Production-grade harness
- 60-79: Functional with gaps — run specific /harn: commands to fill
- 40-59: Needs hardening — run /harn:init to scaffold missing components
- <40: Minimal harness — strongly recommend full /harn:init
Remediation Guide
For each missing item, suggest the specific /harn:* command:
- Missing security guard →
/harn:guard - Missing quality gate →
/harn:gate - Missing formatter →
/harn:format - Missing trace logging →
/harn:trace - Missing checkpoint →
/harn:checkpoint - Missing AGENTS.md →
/harn:agents-md - Missing context management →
/harn:context
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.
- 3d ago First seen · 48 lines · 42 tokens per session scan A 8bc036f2797a
car-analyzer is a skill published in the GitHub repository sliday/harn (5 stars, last pushed 4mo ago), licensed MIT. It adds 42 tokens to every session and 495 once invoked, about $0.0002 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…