Borrowing it
Nothing to install: this file belongs to l-nmch/hailo-10h-llm-compiler. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/l-nmch/hailo-10h-llm-compiler/main/.claude/skills/preflight/SKILL.mdgit clone --depth 1 https://github.com/l-nmch/hailo-10h-llm-compilerWrote 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/l-nmch/hailo-10h-llm-compiler/preflight)<a href="https://agentmods.dev/skills/l-nmch/hailo-10h-llm-compiler/preflight"><img src="https://agentmods.dev/badge/skills/l-nmch/hailo-10h-llm-compiler/preflight/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/l-nmch/hailo-10h-llm-compiler/preflight"><img src="https://agentmods.dev/badge/skills/l-nmch/hailo-10h-llm-compiler/preflight.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.00660 |
| Opus 5 | $0.00019 | $0.00330 |
| Sonnet 5 | $0.00008 | $0.00132 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
preflight scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preflight check
This repo must stay redistributable and evergreen at all times (see CONTRIBUTING.md). Run these checks on the staged/changed files before committing — not just once at repo creation.
1. No proprietary binaries tracked
git ls-files | grep -iE '\.(whl|hef|alls|hn)$|firmware'
Expect empty output. Also check untracked files about to be added:
git status --short
Anything matching those extensions must never be git added, even
temporarily.
2. No dates or timelines in content
grep -rniE '\b(20[12][0-9]-[0-9]{2}-[0-9]{2}|january|february|march|april|june|july|september|october|november|december)\b' \
docs/ README.md CONTRIBUTING.md pipeline/ runtime/ 2>/dev/null
Watch for false positives (e.g. the word "may" as a verb) — read matches, don't just count them. Real dates/changelog language must be rewritten as evergreen prose.
3. No leaked internal infrastructure
grep -rniE 'hpc0|hpc1|10\.5\.0\.1|/home/[a-z]+-[a-z]+' \
--include='*.md' --include='*.py' --include='*.ipynb' . 2>/dev/null | grep -v '.git/'
Any internal hostname, private IP, or absolute path under a personal
$HOME must be genericized (e.g. $DFC_WORKDIR, your-host) before
committing. A GitHub username in .github/FUNDING.yml is fine — that's
attribution, not a leak.
4. Large-file sanity
git ls-files -z | xargs -0 du -h 2>/dev/null | sort -rh | head -10
Nothing here should be a multi-MB artifact; the pipeline never writes
outputs inside the repo tree ($DFC_WORKDIR is external — see
CONTRIBUTING.md code style rules).
5. Structural consistency
- Does the README's "Repository layout" tree still match
find . -maxdepth 2? - If a new
docs/findings/*.mdwas added, is it linked from docs/findings/index.md? - If docs/status.md claims changed, did the underlying stage-by-stage table get updated too?
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.
- 11d ago First seen · 64 lines · 39 tokens per session scan A 29bf8018aa07
preflight is a skill published in the GitHub repository l-nmch/hailo-10h-llm-compiler (14 stars, last pushed 11d ago), licensed MIT. It adds 39 tokens to every session and 660 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
trulens-evaluation-setup
Configure feedback functions and selectors for TruLens evaluations.
trulens-instrumentation
Instrument LLM apps with TruLens OTEL-based tracing - from setup to debugging and optimization.
trulens-diagnosis
Diagnose low evaluation scores and generate actionable improvement recommendations.
trulens-evaluation-workflow
Systematically evaluate your LLM application with TruLens.
trulens-blocking-guardrails
Configure and use feedback functions as runtime blocking guardrails.
trulens-dataset-curation
Create and curate evaluation datasets with ground truth for TruLens.