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/posit-dev/open-source-website/check-postnpx skills add posit-dev/open-source-website --skill check-postgit clone --depth 1 https://github.com/posit-dev/open-source-websiteWhat 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 | $0.00010 | $0.00943 |
| Opus 5 | $0.00005 | $0.00472 |
| Sonnet 5 | $0.00002 | $0.00189 |
| Haiku 4.5 | $0.00001 | $0.00094 |
Grade A, and why
check-post 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 2d 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.
Run the blog post validation script and help the user fix any issues found.
Step 1: Identify the post
If the user provided a path in their request, use that. Otherwise, look for blog posts changed on the current branch:
git diff --name-only --diff-filter=d origin/main...HEAD -- 'content/blog/**/index.md' 'content/blog/**/index.qmd'
If no changed posts are found, ask the user which post to check.
Step 2: Check for unrendered .qmd files
For each post directory found, check if an index.qmd exists. If it does, check whether index.md also exists and is newer than index.qmd:
# For each post directory
if [ -f index.qmd ] && { [ ! -f index.md ] || [ index.qmd -nt index.md ]; }; then
echo "index.qmd has not been rendered to index.md (or is out of date)"
fi
If any .qmd files need rendering, warn the user and always offer to re-render — even if there is no computational environment setup. To render:
quarto render <path>/index.qmd
.qmd posts may need to render through a specific environment — check the post folder for a pyproject.toml, renv.lock, or similar, and use whatever tool the author set up. See the "Setting up an environment" section of content/blog/_authoring-guide.md for context.
Do not proceed with validation until index.md exists and is up to date for all posts.
Step 3: Run validation
The validation script reads index.md files (not .qmd):
uv run scripts/validate-blog-posts.py <paths to index.md>
Step 4: Report results
If all checks pass, say so and stop.
If there are issues, summarize them clearly grouped by severity:
- Errors need fixing before the post can be published.
- Warnings are worth reviewing but won't block publishing — and some are reasonable to leave alone (see below).
For each error, explain what's wrong and suggest a concrete fix. For example:
- Missing
topics→ suggest values fromdata/topics.yamlthat fit the post content - Unknown
software→ check if there's a close match incontent/software/. If there isn't one, offer to create a new software page usingscripts/create-new-software.py. - Unknown
people→ check if there's a close match incontent/people/. If there isn't one, offer to create a new people page. - Missing
sourceon a ported post → suggest setting it to matchported_from categoriespresent → replace withtopics
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.
- 2d ago First seen · 88 lines · 10 tokens per session scan A f193e9d1bf32
check-post is a skill published in the GitHub repository posit-dev/open-source-website (50 stars, last pushed 3d ago), licensed MIT. It adds 10 tokens to every session and 943 once invoked, about $0.0001 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
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.