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/drn/dots/prompt-summarynpx skills add drn/dots --skill prompt-summarygit clone --depth 1 https://github.com/drn/dotsWrote 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/drn/dots/prompt-summary)<a href="https://agentmods.dev/skills/drn/dots/prompt-summary"><img src="https://agentmods.dev/badge/skills/drn/dots/prompt-summary.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00044 | $0.00426 |
| Opus 5 | $0.00022 | $0.00213 |
| Sonnet 5 | $0.00009 | $0.00085 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
prompt-summary 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 4d 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.
What it actually says
Prompt Summary
Review the conversation history and produce a concise numbered list of the user prompts that drove this session.
Instructions
Step 1: Extract Prompts
Scan the full conversation history. Collect every user-submitted prompt in order. Exclude:
- System prompts and injected context
- Slash command invocations (e.g., /test, /pr) unless the user typed additional instructions with them
- Tool approval responses (yes/no clicks)
- Empty or whitespace-only messages
Step 2: Classify Each Prompt
Tag each prompt as one of:
- investigation -- directed research, exploration, or analysis
- implementation -- requested code changes, file creation, or builds
- refinement -- adjusted output format, wording, scope, or style
Step 3: Format the Output
Produce a numbered list. Each entry has the prompt text (quoted or paraphrased to stay concise) followed by a brief annotation of what it accomplished.
Format:
1. "the prompt text" -- what it accomplished
2. "the prompt text" -- what it accomplished
Rules:
- One line per prompt, no sub-bullets or headers
- Paraphrase long prompts to keep each line scannable (aim for under 120 characters for the prompt portion)
- Keep annotations to half a sentence
Step 4: Add a Summary Line
End with a single line summarizing prompt count by phase. Group adjacent prompts of the same type.
Example: "Three prompts for investigation, two for refinement."
Only count phases that actually appeared. Do not force all three categories.
Output
Print the numbered list and summary line directly -- no code fences, no headers, no preamble. The output should be immediately copy-pasteable into Slack or a document.
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.
- 4d ago First seen · 54 lines · 44 tokens per session scan A abec40be2daa
prompt-summary is a skill published in the GitHub repository drn/dots (23 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 426 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 2026-08-30.
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…