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/ahepi/deepreason/dr-capture-requestnpx skills add AHepi/DeepReason --skill dr-capture-requestgit clone --depth 1 https://github.com/AHepi/DeepReasonWhat 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 | $0.00037 | $0.00538 |
| Opus 5 | $0.00018 | $0.00269 |
| Sonnet 5 | $0.00007 | $0.00108 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
dr-capture-request 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capture the request
Input: the operator's message(s). Output: REQUEST.md. You quote; you
do not paraphrase, improve, or fill gaps. Interpretation happens in
dr-spec-change, where it is visible and reviewable — not here, where
it would silently replace the operator's words.
Procedure
- Copy the operator's suggestion VERBATIM into a quoted block. If the suggestion spans several messages (including earlier in the conversation), quote each with its position. Do not trim "context" — trimmed context is how inputs get forgotten.
- Split into atomic requirements R1..Rn. Atomic = one testable obligation each. Split conjunctions ("do X and then Y" → R1: X, R2: Y). Keep the operator's own words in each requirement; add nothing.
- Capture constraints stated anywhere in the conversation that bind this change (deadlines, "don't touch X", style preferences, budget remarks like "prioritise this"). These become C1..Cn with verbatim quotes.
- Mark each requirement's kind:
behavior(code must act differently),artifact(a file/document/skill must exist),process(how the work must be done, e.g. "commit as you go"). - List open questions Q1..Qn — places where the words genuinely underdetermine the work. Do NOT answer them here.
REQUEST.md template
# Request: <operator's own headline words>
Captured: <date> from <operator message position(s)>
## Verbatim
> <exact quote(s)>
## Requirements
R1 (<kind>): "<operator's words for this obligation>"
R2 (<kind>): ...
## Standing constraints
C1: "<verbatim>" — <where stated>
## Open questions (for dr-spec-change)
Q1: <what the words leave undetermined>
## Amendments
(append-only; later operator messages land here as R<n+1>... or
"R2a supersedes R2", each with its verbatim quote)
Exit criteria
- REQUEST.md committed and pushed.
- Zero interpretation performed: every R and C contains a quote.
- Return to the orchestrator.
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 · 60 lines · 37 tokens per session scan A d500ad66125d
dr-capture-request is a skill published in the GitHub repository AHepi/DeepReason (140 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 538 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…