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 itaywol/adeptability --skill authoring-adept-agentsgit clone --depth 1 https://github.com/itaywol/adeptabilityWrote 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/itaywol/adeptability/authoring-adept-agents)<a href="https://agentmods.dev/skills/itaywol/adeptability/authoring-adept-agents"><img src="https://agentmods.dev/badge/skills/itaywol/adeptability/authoring-adept-agents.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 | $0.01216 |
| Opus 5 | $0.00023 | $0.00608 |
| Sonnet 5 | $0.00009 | $0.00243 |
| Haiku 4.5 | $0.00005 | $0.00122 |
Grade A, and why
authoring-adept-agents scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring a good adept agent
An agent is a single file .adeptability/agents/<id>.md (YAML frontmatter + a markdown body
that becomes the agent's entire system prompt). adept sync renders it into every enabled
harness that supports agents — Claude Code, OpenCode, Cursor, Copilot, and Codex — so write it
once, well, and harness-neutral.
Canonical agent format
---
id: pr-reviewer # ^[a-z0-9](?:[a-z0-9-]{0,48}[a-z0-9])?$ — matches the filename
description: Adversarially reviews drafted changes. Use proactively before every commit.
mode: subagent # subagent | primary | all (OpenCode; default subagent)
tools: [Read, Grep, Bash] # allowlist; OMITTED = inherit every tool
disallowed-tools: [Write] # denylist (Claude Code)
model: inherit # verbatim pass-through; grammars differ per harness
targets: [] # empty = every enabled harness
harness: # per-harness knobs (permissionMode, readonly, sandbox_mode, …)
cursor: { readonly: true }
---
You are an adversarial reviewer. ...
adept agent check <id> runs a safety scan plus a best-practice lint over all of this — let
it catch your mistakes.
The description is the delegation trigger — write it like one
Every harness decides whether to hand work to your agent from the description alone.
- State what it does AND when to invoke it: "Reviews Go changes for error-handling bugs. Use after editing internal/ packages."
- Auto-fire intended? Say so: "use proactively", "use immediately after …" — Claude Code and Cursor document this phrasing as the delegation lever.
- One job per agent. No generic helpers; job-shaped names (
test-runner,pr-reviewer). Near-duplicate descriptions across agents make automatic delegation unreliable.
Separate the generator from the evaluator
An agent asked to grade its own output praises it — it sees its chain of self-persuasion, not
the result. Structure work as maker–checker: one agent writes, a different agent judges.
When writing evaluator agents (adept agent add my-reviewer --template evaluator):
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 · 104 lines · 47 tokens per session scan A 43e2f4c9e49c
authoring-adept-agents is a skill published in the GitHub repository itaywol/adeptability (9 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 1,216 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 2026-08-31.
Other skills, from other repositories
ai-orchestration-langchain
LangChain.js patterns for building LLM applications — chat models, LCEL chains, prompt templates, structured output, agents, tools, RAG, streaming, and LangSmith tracing.
ai-provider-cohere-sdk
Official Cohere TypeScript SDK patterns -- CohereClientV2, chat, embeddings, rerank, RAG with citations, tool use, streaming, and model selection.
api-baas-appwrite
Appwrite backend-as-a-service — Auth, TablesDB, Storage, Functions, Realtime, permissions model, typed client.
api-database-mongodb
Native MongoDB driver (the mongodb npm package) - MongoClient lifecycle, typed collections, CRUD result shapes, cursors, aggregation pipelines, index design, transactions.
api-database-redis
Redis in-memory data store patterns with ioredis and node-redis -- caching, sessions, rate limiting, pub/sub, streams, queues, transactions, cluster.
web-meta-framework-sveltekit
SvelteKit full-stack framework - file-based routing, load functions, form actions, server hooks, SSR/SSG, API routes, streaming, progressive enhancement.