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 cnkang/nginx-markdown-for-agents --skill nginx-markdown-harness-maintenancegit clone --depth 1 https://github.com/cnkang/nginx-markdown-for-agentsWrote 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/cnkang/nginx-markdown-for-agents/nginx-markdown-harness-maintenance)<a href="https://agentmods.dev/skills/cnkang/nginx-markdown-for-agents/nginx-markdown-harness-maintenance"><img src="https://agentmods.dev/badge/skills/cnkang/nginx-markdown-for-agents/nginx-markdown-harness-maintenance/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/cnkang/nginx-markdown-for-agents/nginx-markdown-harness-maintenance"><img src="https://agentmods.dev/badge/skills/cnkang/nginx-markdown-for-agents/nginx-markdown-harness-maintenance.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 | $0.00064 | $0.01040 |
| Opus 5 | $0.00032 | $0.00520 |
| Sonnet 5 | $0.00013 | $0.00208 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
nginx-markdown-harness-maintenance 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NGINX Markdown Harness Maintenance
Keep harness changes aligned with repo-owned truth surfaces and run the right verification matrix with minimal guesswork.
Quick Start
- Resolve current spec intent:
python3 tools/harness/resolve_spec.py --hint "<task summary>" - Route changed files to risk packs:
python3 skills/nginx-markdown-harness-maintenance/scripts/harness_route.py --from-git - Run cheap blockers first:
make harness-check - Run focused or umbrella checks from the route output.
- If docs/release wiring changed, run:
make harness-check-full
Example Output
$ python3 skills/nginx-markdown-harness-maintenance/scripts/harness_route.py --from-git
files: 2
- docs/harness/README.md
- docs/harness/HARNESS_MAINTENANCE.md
matched risk packs: 1
- docs-tooling-drift (docs/harness/risk-packs/docs-tooling-drift.md)
path hits:
- docs/harness/HARNESS_MAINTENANCE.md
- docs/harness/README.md
keyword hits:
- docs
verification families: 3
- [cheap-blocker] docs-tooling
- [cheap-blocker] harness-sync
- [umbrella] release-quality
Workflow
- Treat
AGENTS.mdanddocs/harness/as canonical contract surfaces. - Use
tools/harness/resolve_spec.pybefore broad edits. If status isWARN_NEEDS_AUTHOR_REVIEW, stop and explain ambiguity before continuing. - Use
python3 skills/nginx-markdown-harness-maintenance/scripts/harness_route.py --from-gitto map changed files/hints to risk packs and verification families fromdocs/harness/routing-manifest.json. - Build a phased matrix:
cheap-blockerfirst- then
focused-semantic - then
umbrellaonly when needed
- On first drift trigger:
- identify minimal changed files related to the failing family
- rerun only affected verification family commands
- run
make harness-checkbefore broad retries - if drift repeats, escalate with full error output and affected surfaces
- Keep optional local adapters optional. Missing local files must degrade as
SKIP_NOT_PRESENT, not repository failure. - If harness behavior changes, update repo truth in the same change set:
AGENTS.md,docs/harness/,tools/harness/,Makefile, CI workflow.
What ships with it
5 files 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.
- 6d ago Changed fd91e130ac5e
- 11d ago First seen · 89 lines · 64 tokens per session scan A 1aaf00ea8034
nginx-markdown-harness-maintenance is a skill published in the GitHub repository cnkang/nginx-markdown-for-agents (23 stars, last pushed yesterday), licensed BSD-2-Clause. It adds 64 tokens to every session and 1,040 once invoked, about $0.0003 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
firecrawl-build
Integrate Firecrawl into application code whenever a product, agent, or workflow needs web data inside the app — web search, live search results, page scraping, structured extraction, or browser interaction. Use when building any feature that needs data from the web in code, even if the user does not mention Firecrawl…
firecrawl-build-onboarding
Get Firecrawl credentials and SDK setup into a project. Use when an application needs FIRECRAWLAPIKEY, when an agent should add Firecrawl to .env, when the user wants to authenticate Firecrawl for app code, or when choosing the first SDK and docs for a new Firecrawl integration. This skill includes its own browser…
firecrawl-build-scrape
Integrate Firecrawl /scrape into product code for single-page extraction. Use when an app already has a URL and needs markdown, HTML, links, screenshots, metadata, or structured page output. Prefer this skill over broader crawl patterns when the feature is page-level.
firecrawl-build-search
Integrate Firecrawl /search into product code and agent workflows. Use when an app needs discovery before extraction, when the feature starts with a query instead of a URL, or when the system should search the web and optionally hydrate result content.
firecrawl-build-interact
Integrate Firecrawl /interact into product code for dynamic pages and browser actions after scraping. Use when a feature needs clicks, form fills, pagination, authentication-aware flows, or other multi-step interactions that plain /scrape cannot complete.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.