hecate-devops

A delivery-safety review for software changes that affect configuration, databases, deployments, monitoring, or release work. It checks the surrounding systems and the path for recovering from problems.

In plain words
What is it for?
Use it when changing environment variables, database schemas, CI/CD workflows, public endpoints, data-retention workers, monitoring signals, or release procedures.
Why use it?
It helps reveal operational risks that may not appear in the code itself. It also checks whether configuration, documentation, automation, and monitoring changes fit together.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/hecatehq/hecate/devops
Any agent
npx skills add hecatehq/hecate --skill devops
Clone the repo
git clone --depth 1 https://github.com/hecatehq/hecate

Made for: Claude Code, Codex.

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 733 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00031 $0.00733
Opus 5 $0.00015 $0.00367
Sonnet 5 $0.00006 $0.00147
Haiku 4.5 $0.00003 $0.00073

Measured 2d ago against content hash 5eff6dfbde4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hecate-devops 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 2d 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.

docs-ai/skills/devops/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hecate devops skill

Delivery-readiness review. Surfaces risk explicitly.

When to use

Anything with a CI/CD, environment, deploy, or migration footprint:

  • New env vars or changed defaults.
  • Schema changes across storage tiers (memory + SQLite + Postgres).
  • CI/CD workflow changes.
  • New public HTTP endpoints (downstream SDKs depend on them).
  • Retention worker changes (new subsystem, changed cadence, retention windows).
  • OTel surface changes (new spans, new metrics, new error codes).
  • Release-note drafting and tag-cutting — see ../../tasks/release.md for the procedure (snapshot dry-run, verification gate, footguns, recovery).

Surfaces to check

  • CI/CD. Which workflow files run? Will paths-ignore skip this change accidentally? Does the change need a [skip ci] marker, or does it require CI to actually run?
  • Environment. New env vars must land in .env.example AND the relevant docs/operator/, docs/runtime/, docs/contributor/, or docs/design/ page — same change, not as a follow-up. Stale env-var docs cause more on-call pages than missing features.
  • Config compatibility. Does an old config still boot? If not, that's a breaking change — needs a migration note in the commit body.
  • Schema migrations. Which storage tiers are affected? Memory is rebuilt on boot (fine). SQLite and Postgres need forward-compatible migrations and roll-forward considerations. The retention worker subsystems (traces, usage_events, audit, provider_history, model_call_events, chat_approvals) must keep mirroring.
  • Deploy and release risk. Is this safe to roll out behind a flag? Does it need a flag at all? What's the blast radius if it misbehaves?
  • Rollback. Can this change be reverted cleanly? If a schema change is involved, is the rollback path documented?
  • Observability. New code paths get OTel spans, not just log lines. Stable error codes for new failure modes (see internal/api/error_mapping.go). Trace IDs surfaced.
  • Release notes. When relevant, draft them in the commit body so they're easy to lift later.

Read the full file on GitHub · 53 lines

Changes

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.

  1. 2d ago First seen · 53 lines · 31 tokens per session scan A 5eff6dfbde4e

Subscribe to this mod's changes

hecate-devops is a skill published in the GitHub repository hecatehq/hecate (22 stars, last pushed 8d ago), licensed MIT. It adds 31 tokens to every session and 733 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.