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/hecatehq/hecate/backendnpx skills add hecatehq/hecate --skill backendgit 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/backend)<a href="https://agentmods.dev/skills/hecatehq/hecate/backend"><img src="https://agentmods.dev/badge/skills/hecatehq/hecate/backend.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 | $0.00047 | $0.15832 |
| Opus 5 | $0.00023 | $0.07916 |
| Sonnet 5 | $0.00009 | $0.03166 |
| Haiku 4.5 | $0.00005 | $0.01583 |
Grade A, and why
hecate-backend 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 6d 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 — 1,077 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hecate backend skill
Use this skill for any work outside ui/. The React UI has its own skill at ../ui/SKILL.md. For the internal/providers/ package specifically, also reach for ../providers/SKILL.md — it owns the api↔providers boundary and the seven-step "add a wire field" chain.
Canonical guidance lives here
Don't duplicate. This skill is the backend lens; the rules themselves live in:
../../core/project-context.md— repo layout, rings, storage tiers, toolchain pins, risky areas.../../core/engineering-standards.md— field-shape rules, parallel-struct rule, anti-patterns.../../core/workflow.md— operating loop, planning triggers, commit etiquette.../../core/verification.md— verification ladders, race-suite floor, done criteria.
Product lens
The backend should feel like:
- A single-process gateway control plane.
- A deny-by-default policy enforcer.
- A runtime-aware proxy that explains its decisions.
- A debugging surface — every request leaves a trace, every cost is itemized, every approval is logged.
It should not feel like:
- A thin pass-through with marketing on top.
- A configurable framework where you bring your own everything.
- A research demo that works in one provider's happy path.
Default to operator confidence: clear status, clear errors, deterministic state, no surprises on restart.
Engineering thesis
Calm, durable, and explicit. Code should age well — the runtime is supposed to live for years, not iterations.
Prefer one gateway process, one port, embedded UI (//go:embed ui/dist); deterministic startup with env-driven config; backend tier choice surfaced as a config knob, never inferred; explicit error wrapping with cause chains; standard library first, well-known third party second, novel deps last.
Operator priorities
Every endpoint, every config knob, every error message should answer:
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.
- 6d ago First seen · 1,077 lines · 47 tokens per session scan A 1b8fc9221fa9
hecate-backend is a skill published in the GitHub repository hecatehq/hecate (22 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 15,832 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
changelog-writer
Write changelogs for Bifrost releases. Reads git history, bumps module versions following the core→framework→plugins→transport hierarchy, writes transports/changelog.md (enterprise-style) and per-module changelog.md files, and updates version files. Invoked with /changelog-writer or /changelog-writer .
resolve-pr-comments-stack
Resolve unresolved PR review comments across an entire Graphite (gt) stack of many PRs, bottom-up, in one working directory. Use when asked to "go through this stack and resolve comments", "clean up review comments across the whole stack", or given a list/range of PR numbers that form (or partially form) a gt stack.…
split-commit-into-stack
Split one oversized commit or branch into a stack of independently reviewable Graphite (gt) PRs - deciding what genuinely separates, what is atomic and must stay whole, and proving each lower PR builds and passes without the ones above it. Use when asked to "split this PR", "this commit is too big", "break this into a…
resolve-pr-comments
Skill "resolve-pr-comments" from maximhq/bifrost, covering resolve pr comments, usage, workflow overview, step 1: detect repository and step 2: fetch unresolved comments (graphql).
stack-absorb
Manually distribute working-tree changes (or a batch of edits already made on the current branch) across the correct branches of a Graphite (gt) stack, when gt absorb's blame-based auto-split doesn't match the logical grouping - e.g. new code with no prior line to blame onto, or changes that conceptually belong with a…
helm-update
Apply helm chart updates for Bifrost. Detects config.schema.json changes since the last helm release, applies user-requested changes, updates values.yaml / values.schema.json / helpers.tpl, bumps Chart.yaml version, updates helm README (Latest Version + Upcoming section), creates a docs MDX changelog, and updates…