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/sapiom/sapiom-js/sapiom-agent-authoringnpx skills add sapiom/sapiom-js --skill sapiom-agent-authoringgit clone --depth 1 https://github.com/sapiom/sapiom-jsWhat 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 | $0.00157 | $0.08710 |
| Opus 5 | $0.00078 | $0.04355 |
| Sonnet 5 | $0.00031 | $0.01742 |
| Haiku 4.5 | $0.00016 | $0.00871 |
Grade A, and why
sapiom-agent-authoring 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.
How it starts
The opening of the file, as written. The whole thing — 713 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building Sapiom Agents
A Sapiom agent is a small TypeScript project you author with your coding agent: a
defineAgent({ name, entry, steps }) where each step's run(input, ctx) does work — calling
paid Sapiom capabilities through the typed ctx.sapiom.* client — and returns a directive.
You test it locally without a Sapiom account or capability spend, then deploy it to run on
Sapiom's cloud: on demand, on a schedule, or resumed by signals. All from the terminal; no
dashboard required.
Load this skill before scaffolding — it drives the whole lifecycle from zero. Inside a
scaffolded project, AGENTS.md is the quick reference; this skill is the deep guide.
If the Sapiom dev MCP isn't connected yet
The lifecycle below runs through the sapiom-dev MCP server (@sapiom/mcp). If its tools
(sapiom_authenticate, sapiom_dev_agents_*) aren't available, add the server first:
claude mcp add sapiom -- npx -y @sapiom/mcp
Other clients: run npx -y @sapiom/mcp as a local (stdio) MCP server — see
docs.sapiom.ai for per-client config.
Lifecycle from Zero
1. Scaffold
Call sapiom_dev_agents_scaffold with a target directory. The scaffold writes:
my-agent/
├── index.ts # your agent definition (edit this)
├── AGENTS.md # quick in-project reference
├── CLAUDE.md # points your coding agent at AGENTS.md
├── .claude/skills/ # this skill, locally — the deep guide
├── .sapiom-dev/stubs.json
├── package.json / tsconfig.json / ...
Install deps: npm install. Templates: "default" (minimal two-step starter) or
"coding-pause" (launch + pause/resume coding-model pattern).
2. Write steps → typecheck → check → run_local
| Command | What it does |
|---|---|
npm run typecheck |
Confirms types compile and every ctx.sapiom.* call exists |
sapiom_dev_agents_check |
Typechecks, bundles and imports index.ts, then validates the manifest and graph; no Sapiom account or service call |
sapiom_dev_agents_run_local |
Runs real step code with ctx.sapiom.* calls stubbed — no Sapiom capability spend |
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.
- 2d ago First seen · 713 lines · 157 tokens per session scan A 0c2d6b827f0a
sapiom-agent-authoring is a skill published in the GitHub repository sapiom/sapiom-js (19 stars, last pushed 2d ago), licensed MIT. It adds 157 tokens to every session and 8,710 once invoked, about $0.0008 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.