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/disler/pi-agent-observability/htmlspecnpx skills add disler/pi-agent-observability --skill htmlspecgit clone --depth 1 https://github.com/disler/pi-agent-observabilityWhat 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 | $0.00123 | $0.03115 |
| Opus 5 | $0.00062 | $0.01558 |
| Sonnet 5 | $0.00025 | $0.00623 |
| Haiku 4.5 | $0.00012 | $0.00312 |
Grade A, and why
htmlspec 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.
How it starts
The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.
htmlspec
Purpose
Produce an engineering implementation plan as one self-contained, text-only HTML page —
specs/<plan-name>.html — that you can open directly in a browser. Unlike a markdown spec,
the plan is authored directly in HTML using the template below, and a dedicated
Freeform zone lets you author any HTML you want (interactive toggles, animated SVG flows,
comparison matrices, decision trees, etc.) to make the plan clearer and richer than prose
could. No images are generated — all visual enrichment comes from inline HTML, CSS, SVG,
and JS authored directly into the page.
Phases, in order:
- Plan phase — analyze, explore, design (same thinking as a normal spec).
- HTML authoring phase — write the plan into the HTML Plan Template.
- Freeform phase — enrich the page with custom HTML per the Freeform Instruction Set.
Variables
USER_PROMPT: $1
ALL_ARGUMENTS: $ARGUMENTS
PLAN_OUTPUT_DIRECTORY: specs/
PLAN_SLUG: kebab-case name derived from the plan topic (e.g. in-memory-ttl-lru-cache)
HTML_OUTPUT: specs/htmlspec-<PLAN_SLUG>.html — the filename MUST always begin with the htmlspec- prefix
Instructions
Plan phase
- IMPORTANT: If no
USER_PROMPTis provided, stop and ask the user to provide it. - Carefully analyze the USER_PROMPT. Determine task type (chore|feature|refactor|fix|enhancement) and complexity (simple|medium|complex).
- Think deeply (ultrathink) about the best implementation approach.
- Explore the codebase to understand existing patterns and architecture.
- Decide which sections from the HTML Plan Template apply (include the conditional sections only when task type/complexity warrants them, exactly like a normal spec).
- Generate a descriptive kebab-case PLAN_SLUG from the topic.
HTML authoring phase
- Author the plan directly in HTML using the HTML Plan Template below — do not write a markdown file. The output is a single
specs/htmlspec-<PLAN_SLUG>.html. - Keep the page self-contained: all CSS inline in
<style>, any JS inline in<script>, no external network/CDN dependencies unless genuinely required (and if so, note it in Notes). - Fill every applicable section with real, detailed content — the plan must be implementable by another developer. Use semantic HTML:
<ul>/<ol>for lists,<table>for comparisons,<pre><code>for code/commands. - Preserve the dark visual theme defined by the template's CSS tokens so the page reads as one body of work.
- Do not include any
<figure>/<img>elements — this skill is text-only.
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 · 243 lines · 123 tokens per session scan A 4d9687c985e5
htmlspec is a skill published in the GitHub repository disler/pi-agent-observability (142 stars, last pushed 3mo ago), licensed MIT. It adds 123 tokens to every session and 3,115 once invoked, about $0.0006 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.
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…