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 instructions/skael-dev/skael/claude-mdgit clone --depth 1 https://github.com/skael-dev/skaelWrote 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/instructions/skael-dev/skael/claude-md)<a href="https://agentmods.dev/instructions/skael-dev/skael/claude-md"><img src="https://agentmods.dev/badge/instructions/skael-dev/skael/claude-md.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 | $0.11322 | $0.11322 |
| Opus 5 | $0.05661 | $0.05661 |
| Sonnet 5 | $0.02264 | $0.02264 |
| Haiku 4.5 | $0.01132 | $0.01132 |
Grade C, and why
skael CLAUDE.md scanned grade C with 2 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 today.
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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- `internal/gate/` — `Decide` takes no database, HTTP, context or clock, so every policy question is answerable by a table test. Appealability is **per-rule**, not per-category: `Rule.Class` overrides the class derived f Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `internal/gate/` — `Decide` takes no database, HTTP, context or clock, so every policy question is answerable by a table test. Appealability is **per-rule**, not per-category: `Rule.Class` overrides the class derived f How it starts
The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What is Skael
Skael is a self-hostable platform + CLI for managing AI agent skills (SKILL.md files) across engineering teams. It provides a central registry, cross-agent sync, security scanning, and activation tracking. See docs/prd.md for the full product context.
Commands
Uses just as the task runner. Run just to see all commands. Key ones:
just build # build binaries to bin/ (server, skael, whetstone, skael-worker)
just dev # run server (reads .env)
just db # start Postgres in Docker
just test # all tests (needs Docker for testcontainers)
just test-fast # fast tests without DB (instant)
just test-pkg internal/scan # single package
just test-run TestStore_Create # single test by name
just test-e2e # browser e2e (Playwright, needs dev server + db)
just test-integration # Go integration e2e (real server + testcontainers)
just check # vet + fmt-check + test + integration e2e + web tests (CI)
just scan ./path # security scan a skill directory
just migrate # run pending migrations
just migrate-down # rollback last migration
just migrate-status # show migration status
just migrate-create add_foo # create a new migration file
Migrations use goose. SQL files live in internal/platform/migrate/ with -- +goose Up and -- +goose Down annotations. Migrations run automatically on server startup and in tests via testutil.SetupTestDB.
Server reads config from .env (see .env.example). Copy it before first run: cp .env.example .env
Architecture
Three binaries from one Go module (github.com/skael-dev/skael):
cmd/server — HTTP API server. Chi router + Huma v2 (auto-generates OpenAPI spec). Embeds a React SPA via embed.FS from web/dist/. Auth via user accounts (bcrypt passwords, session cookies) + personal API keys (SHA-256, X-API-Key header). Middleware stack: security headers, request ID, CORS, per-route-class rate limiting, request logging. Auth middleware skips /api/health, /api/health/ready, /api/openapi.json, /api/capabilities, /api/auth/signup, /api/auth/login, /api/auth/logout, and /metrics. Subcommand reset-password --email for operator-run password recovery (requires direct database access; run by whoever operates the server, not the admin role).
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.
- today Changed · +23 lines · +1,537 tokens per session 0863dbef23af
- 4d ago First seen · 213 lines · 9,785 tokens per session scan C ab86091dad6e
skael CLAUDE.md is an instructions file published in the GitHub repository skael-dev/skael (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 11,322 tokens to every session, about $0.0566 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
lola AGENTS.md
AGENTS.md instructions for LobsterTrap/lola, covering lola — agent instructions, working in this repo, development commands, python and go.
loom CLAUDE.md
Claude Code instructions for cosmix/loom, covering claude.md, project overview, build commands, architecture and source layout (loom/src/).
chart-visualization-skills CLAUDE.md
Claude Code instructions for antvis/chart-visualization-skills: See AGENTS.md for project architecture and structure.
truthmark AGENTS.md
AGENTS.md instructions for merlinhu1/truthmark, covering authority, documentation scope, product boundary, rules and instruction surface boundary.
skills-manager AGENTS.md
Instructions for cchao123/skills-manager, covering agents.md, project overview, development commands, start development server and build production bundle.
AmbyKit AGENTS.md
Instructions for ambystechcom/AmbyKit, covering agents.md — ambykit, what ambykit is, golden rules, project structure and build & test.