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/rafaelszago/doc-everything/document-feature-technicalnpx skills add rafaelszago/doc-everything --skill document-feature-technicalgit clone --depth 1 https://github.com/rafaelszago/doc-everythingWrote 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/rafaelszago/doc-everything/document-feature-technical)<a href="https://agentmods.dev/skills/rafaelszago/doc-everything/document-feature-technical"><img src="https://agentmods.dev/badge/skills/rafaelszago/doc-everything/document-feature-technical.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 | $0.00134 | $0.00965 |
| Opus 5 | $0.00067 | $0.00483 |
| Sonnet 5 | $0.00027 | $0.00193 |
| Haiku 4.5 | $0.00013 | $0.00097 |
Grade A, and why
document-feature-technical 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.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Document a feature — technical
Record the engineering view of a feature: how it actually works, the files that make it up, and the decisions a future maintainer needs. This is the companion to [[document-feature-product]] (the user-facing view).
Where it goes
docs/features/<feature>/technical.md ← this skill
docs/features/<feature>/product.md ← document-feature-product skill
docs/features/README.md ← index (product skill owns it)
<feature>is a kebab-case slug. Match it to how the codebase already names the feature (its module/package/directory) so the docs are easy to trace back.- If this project pins the docs directory elsewhere (via
.claude/doc-everything.jsondocsPath, or the plugin'sDOC_EVERYTHING_DOCS_PATHenv var), use that path instead ofdocs/features/. - One file per feature — update the existing
technical.mdin place, don't spawntechnical-v2.md. Keep it current with the code, not a changelog.
How to write it
- Read the code first. Describe what the code actually does today, never aspirational or planned behavior. If the project has architectural conventions (a data-access layer, a service pattern, a module boundary), describe the feature in those terms.
- Fill the template below. Drop sections that genuinely don't apply — say so in one line rather than leaving an empty stub.
- Link real files as clickable references (
path/to/file:line), and cross-link the matchingproduct.md. - When you change a feature, update the affected sections (data model, files, decisions) — stale technical docs are worse than none.
Template
# <Feature> — technical
> Product view: ./product.md
## Summary
One or two lines: what this feature does at the system level.
## Status
scaffolded | in progress | shipped — and a line on what's real vs stubbed.
## Architecture & data flow
How it fits the app's architecture. Trace one representative action end to end
(what the user/client triggers → each layer it passes through → where it lands).
Note where reads come from vs where writes go.
## Files & responsibilities
| File | Role |
|------|------|
| `path/to/entry` | request entry / route / handler |
| `path/to/logic` | core logic / use-case / service |
| `path/to/data` | data access / persistence |
| `path/to/ui` | UI / presentation |
## Data model
Tables/collections/columns or types touched, and the migration(s) or schema
changes that introduced them. Note any fields with special handling.
## Auth, validation & authorization
Where the request is authenticated, where input is validated, and how access is
authorized. Note the trust boundary (what the client is/ isn't allowed to send).
## External dependencies & integrations
Third-party services, APIs, queues, env vars, or feature flags this relies on.
## Key decisions & trade-offs
Why it's built this way; alternatives rejected; known limitations / TODOs.
## Testing
What's covered (unit / integration / e2e), where those tests live, and how to
run them.
## Extending / gotchas
What a future change most likely touches, and traps to avoid.
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 · 96 lines · 134 tokens per session scan A b5b90f6ef6af
document-feature-technical is a skill published in the GitHub repository rafaelszago/doc-everything (2 stars, last pushed 1mo ago), licensed MIT. It adds 134 tokens to every session and 965 once invoked, about $0.0007 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 2026-08-31.
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…