Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/qxbyte/pluginhubnpx agentmods add skills/qxbyte/pluginhub/intakeWrote 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/qxbyte/pluginhub/intake)<a href="https://agentmods.dev/skills/qxbyte/pluginhub/intake"><img src="https://agentmods.dev/badge/skills/qxbyte/pluginhub/intake/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/qxbyte/pluginhub/intake"><img src="https://agentmods.dev/badge/skills/qxbyte/pluginhub/intake.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00085 | $0.02538 |
| Opus 5.5 | $0.00034 | $0.01015 |
| Sonnet 5.5 | $0.00017 | $0.00508 |
| Haiku 4.5 | $0.00009 | $0.00254 |
Grade A, and why
intake 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 24d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
intake — specode's requirements-intake engine
Host-tool convention 🔧: tool names in this skill —
AskUserQuestion(structured multiple-choice question), theSkilltool (invoke another skill by name) — are written for Claude-family hosts (Claude Code / CodeBuddy), where naming them directly is the most reliable. On a host that lacks one, use its nearest equivalent (a structured-question tool / a skill-invocation mechanism); with no equivalent, fall back to a plain-text question / reading the target skill'sSKILL.mddirectly. The described behavior is what matters, not the exact tool name.
§0 Who you are / when you're invoked
- The specode orchestration shell invokes you by name (
specode:intake) via theSkilltool during the requirements phase. By then<specsRoot>is resolved,<specsRoot>/<slug>/exists, and the slug is fixed. - You are the sole producer of
requirements.md— specode no longer forks the requirements phase on "superpowers present or not". superpowers'brainstormingis used only for design from here on; it never moonlights as a requirements writer. - What sets you apart from the old "native 2-4 question wizard" is entirely §Step 2 project analysis + §Step 3 analysis-driven clarification: read the real project first to establish a factual baseline, then ask grounded questions — that is specode's own "driving capability", not a blank questionnaire.
- Your outputs:
<specsRoot>/<slug>/requirements.md— prose requirements plus the hard frontmatter contract (§1);- a block of
参考定位(非事实来源)location pointers handed to the design phase (§5, ephemeral context, never persisted as fact).
§1 Hard constraints 🔒 (never violate)
- Frontmatter contract (highest priority — explicitly required by the user): the YAML at the top of
requirements.mdmust carry three fields —spec_id/created_at/project_root.project_rootis the single source of truth for downstream distill / task-swarm / retrieval, and it may only be written through the single validated writerresolve_root.py write-project-root(it validates absolute path / dir exists //Volumesmount); never hand-write that field. You change who generates the body of requirements, and must never break these contract elements. - Prose requirements:
requirements.mdis a natural-language spec (background / scope in-out /- [ ] AC-N/ open questions), no formalized clauses, no checkboxes — the plan lives in tasks.md and the design in design.md; don't cross that boundary. Bug fixes go here as Current / Expected prose; there is no separatebugfix.md. - User-facing output is Chinese — technical names / paths / code identifiers / frontmatter key names stay verbatim.
- Never reprint the full document (see §5 reporting discipline).
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.
- 24d ago Changed · +2 lines 5f4b75b89324
- 1mo ago First seen · 102 lines · 85 tokens per session scan A 0bc3de0a6d63
intake is a skill published in the GitHub repository qxbyte/pluginhub (3 stars, last pushed 25d ago), licensed MIT. It adds 85 tokens to every session and 2,538 once invoked, about $0.0003 per session on Opus 5.5. 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
shiny-py-optimize
Diagnose and fix performance problems in Shiny for Python apps — slow startup, sluggish interactions, blocking operations, and apps that struggle beyond a handful of concurrent users. Use when a Shiny for Python app is slow, hangs, recomputes too much, times out, or must support more users; when the user asks to…
sync-check
Walks the documentation dependency web after a CLI code change and reports which downstream files (skills, SOPs, READMEs, plugin references) are out of sync. Use after fixing a bug, adding a command, changing auth behavior, refactoring, or before committing — and when the user says "sync check", "update docs"…
gap-analyzer
Compares a CLI's implemented commands against its APP.md API map and traffic-analysis.json to find missing endpoints, incomplete CRUD, dead client methods, and priority gaps. Runs as the mandatory first step of /cli-anything-web:refine and as an optional pre-review scan in standards.
linkedin-cli
Interacts with LinkedIn via the cli-web-linkedin command-line tool — search people/jobs/companies, view profiles and feed, create/edit/delete posts, react and comment, manage connections and invitations, read and send messages, view notifications, follow companies. Use when the user asks about LinkedIn or wants to…
tripadvisor-cli
Searches TripAdvisor hotels, restaurants, attractions, and destinations via the cli-web-tripadvisor command-line tool, with detail lookups by URL. Use when the user asks about hotels, restaurants, things to do, travel destinations, or TripAdvisor ratings and reviews. Prefer this CLI over fetching the TripAdvisor…
youtube-cli
Searches YouTube and fetches video transcripts via the cli-web-youtube command-line tool — video search, video details (views, duration, description, keywords), trending by category, channel info, and timestamped transcripts/captions with language selection and translation. Use when the user asks about YouTube…