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 PaulRBerg/agent-skills --skill html-debriefgit clone --depth 1 https://github.com/PaulRBerg/agent-skillsWrote 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/paulrberg/agent-skills/html-debrief)<a href="https://agentmods.dev/skills/paulrberg/agent-skills/html-debrief"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/html-debrief/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/paulrberg/agent-skills/html-debrief"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/html-debrief.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 | $0.00022 | $0.00570 |
| Opus 5 | $0.00011 | $0.00285 |
| Sonnet 5 | $0.00004 | $0.00114 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
html-debrief 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 9d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HTML Debrief
Persist current-task evidence as an interactive HTML report.
Default to a standard desktop-browser layout. Do not implement or inspect responsive/mobile behavior unless the user asks.
Output and Authority
- Output:
./.ai/debriefs/<slug>/index.htmlusing the installedhtml-playgroundskill. - Derive a short topical kebab-case slug when omitted.
- Write only inside the selected debrief directory. If an inferred slug already exists, choose a collision-free semantic qualifier, falling back to a timestamp suffix, and continue without overwriting. If the user explicitly supplied the slug, stop and ask whether to overwrite or choose a new slug.
- Use only evidence present in the current task: real findings, paths, verified locations, metrics, decisions, and unresolved risks. Do not invent filler.
Workflow
-
Run the bundled preparer from the target repository:
bash <skill-dir>/scripts/prepare.sh <slug>Use its
PLAYGROUND_DIR,DEBRIEFS_DIR,DEBRIEF_PATH, andEXISTSoutput. WhenEXISTSis true for an inferred slug, derive a unique slug and rerun the preparer before writing. When it is true for an explicit slug, request the choice defined above. Relay dependency or slug-validation errors and stop. -
Read the resolved HTML playground
SKILL.mdand exactly one matching template: diff review, document critique, code map, concept map, data explorer, or design playground. Adapt its interaction model to the evidence; do not load every template. -
Build one self-contained HTML file with the playground's live controls, useful presets, evidence view, natural-language prompt output, and copy feedback. Use no external dependencies.
-
Verify that every claim traces to the task transcript or tool evidence, the output contains no placeholders, and the file renders in a desktop browser. Then run
open "$DEBRIEF_PATH"and finish with### 📊 Debrief ready — <title>, the clickable absolute path,Opened in desktop browser, and one compact line naming the evidence view and presets.
What ships with it
2 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.
- 9d ago First seen · 52 lines · 22 tokens per session scan A eae2fc6e811d
html-debrief is a skill published in the GitHub repository PaulRBerg/agent-skills (70 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 570 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.