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 skills add hecatehq/hecate --skill architectgit clone --depth 1 https://github.com/hecatehq/hecateWrote 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/hecatehq/hecate/architect)<a href="https://agentmods.dev/skills/hecatehq/hecate/architect"><img src="https://agentmods.dev/badge/skills/hecatehq/hecate/architect.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 5.1 | $0.00044 | $0.00457 |
| Opus 5 | $0.00022 | $0.00229 |
| Sonnet 5 | $0.00009 | $0.00091 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
hecate-architect 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 7d 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
Hecate architect skill
Plan-shaped responses for substantial changes. The skill produces a plan, not code. Use it when "I am about to make a substantial change; I need to think before I type."
When to use
Any change that triggers a planning event in ../../core/workflow.md:
- Cross-package wire-field changes (the seven-step chain — see
../providers/SKILL.md). - New Hecate-owned persisted things — normally mirror memory + SQLite + Postgres tiers. Portable Projects records belong in Cairnline instead; never add a second Hecate persistence tier for them.
- New HTTP endpoints (provider-compatible
/v1/...or Hecate-native/hecate/v1/...). - New approval policies or sandbox capabilities.
- New persistent UI surfaces (inspector, side rail, dashboard block, summary panel).
- Substantive refactors that cross ring boundaries or touch the api↔providers seam.
When in doubt, default to using this skill. The cost of a brief plan is far less than the cost of an unplanned change that hits the wrong seam.
Bias
Plan first. Do not write code in this skill's response. Unless the task is trivial (typo fix, single-line dependency bump, comment touch-up), produce a plan first.
Output
Use the canonical plan structure and anti-patterns in ../../tasks/planning.md. That doc owns the format; this skill owns when to invoke it.
Hand-off
The plan is the brief for a hecate-backend, hecate-ui, or hecate-providers skill turn. It should give the implementer everything they need to proceed without further context — including the verification ladder they'll run and the docs they'll update.
Verification expectations
None for the plan itself. The plan must enumerate the verification ladder for the implementer.
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.
- 7d ago First seen · 40 lines · 44 tokens per session scan A 14e6b590a86c
hecate-architect is a skill published in the GitHub repository hecatehq/hecate (22 stars, last pushed 4d ago), licensed MIT. It adds 44 tokens to every session and 457 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
trulens-instrumentation
Instrument LLM apps with TruLens OTEL-based tracing - from setup to debugging and optimization.
self-host-studio
Install and self-host deco Studio (the open-source control plane) on the user's own infrastructure. Use when the user wants to install, run, self-host, or deploy Studio locally (Docker, Rancher Desktop, kind, minikube) or on Kubernetes (managed or self-managed), or asks to "install Studio", "self-host decocms"…
slides
Create and edit presentation decks as single self-contained HTML files with a live, editable preview and print-to-PDF export. Use when the user wants slides, a deck, or a presentation.
brand
Create and maintain an org's brand as a folder the whole platform reads: colors, type, voice, logo and a deck theme. Use this whenever someone asks to "set up our brand", "make a brand kit", "apply our colors/fonts", or before producing branded artifacts (decks, pages, emails). One brand = one folder; everything that…
decocms-ui
Build or style React UI with the decocms product design system (@decocms/ui). Use when creating interfaces, pages, or components in a project that should look like decocms products, when the user mentions "design system", "@decocms/ui", "decocms style", or asks to make UI consistent with Studio. Covers installation…
templating
Render any text file (HTML, markdown, config, SQL, email) from a mustache template plus JSON data. Use when an output's shape is fixed ahead of time and only the values change.