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/winterarc21/hqflow/codehqnpx skills add WinterArc21/HQFlow --skill codehqgit clone --depth 1 https://github.com/WinterArc21/HQFlowWhat 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 | $0.00000 | $0.03111 |
| Opus 5 | $0.00000 | $0.01555 |
| Sonnet 5 | $0.00000 | $0.00622 |
| Haiku 4.5 | $0.00000 | $0.00311 |
Grade A, and why
codehq 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 yesterday.
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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HQFlow — Agent Skill
You are documenting how this repository actually behaves, for a tool called HQFlow.
HQFlow has no LLM of its own and never uploads code anywhere — it
only renders the structured JSON files you write here, in .codehq/, as an interactive
workflow canvas that a human can explore in their browser. Your job is to read the real
source code and describe real workflows accurately, honestly, and at the right altitude.
Everything you write goes into .codehq/workflows/<id>.json. HQFlow validates
every file you write, watches this directory, and updates the canvas live. If you make a
mistake, it will tell you exactly what is wrong in .codehq/diagnostics.json — read that
file after every change and fix anything you broke.
The 16 rules
- Start from a real user action, route, handler, server action, event consumer, cron task, or system entry point.
- Trace the relevant code path through the repository.
- Group low-level functions into meaningful product steps.
- Do not expose logging, generic utilities, framework internals, or trivial adapters as top-level steps.
- Prefer five to nine top-level steps for a normal workflow.
- Attach real repository-relative source files and symbols to each step.
- Record important inputs and outputs.
- Record meaningful failure branches and edge cases.
- Attach tests that prove the behavior when they exist.
- Preserve human-written names, notes, and corrections.
- Edit only files inside
.codehqunless the user explicitly asks for source-code changes. - Follow the supplied JSON schema exactly.
- Never add layout coordinates, colors, styling, or visual instructions.
- Run
hqflow validateafter making changes. - Read
.codehq/diagnostics.jsonand repair any errors you introduced. - Write step
nameandpurposein product language a non-author can understand (e.g. "Collect website data", notpollFirecrawlBatch). Keep type and symbol names ininputs/outputs/sources— the canvas shows the product story; expand a card or open the drawer for files, types, and symbols.
What ships with it
1 file 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.
- yesterday First seen · 208 lines · 0 tokens per session scan A 30288d3ad27d
codehq is a skill published in the GitHub repository WinterArc21/HQFlow (21 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,111 tokens. 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.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…