New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Smithers Agent Runtime

by smithersai in smithersai/smithers

Guides changes to the Smithers agent loop's host wiring: credentialed model seats, budget accounting, sandbox limits and flow-call authorization.

MITAuto-check passedAgent Workflows

Install Smithers Agent Runtime

skills CLI
$ npx skills add smithersai/smithers --skill smithers-agent-runtime -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install smithersai/smithers smithers-agent-runtime --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/smithersai/smithers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/smithers-agent-runtime .claude/skills/smithers-agent-runtime && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
smithers-agent-runtime
GitHub stars
430
Token cost
~765 tokens
SKILL.md length
353 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

Guides changes to the Smithers agent loop's host wiring: credentialed model seats, budget accounting, sandbox limits and flow-call authorization.

  • Changing how Smithers resolves model seats, budgets or sandbox limits
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Adding authorization checks around a journaled flow-call activity
  • Wiring a new completion evaluator or scorer into the agent loop

What it does

The skill points to the specific README each kind of change needs before touching host wiring or agent boundaries, since Agent.Service owns a single cell loop and any foreign CLI agent should implement that interface rather than add a second loop. A host resolves credentialed seats through SeatResolver, supplies quota and budget policy, and declares bounded sandbox limits; the completion evaluator used to judge a run is a host decision that must be selected before resources open, refusing missing configuration rather than silently falling back to a scripted or unavailable judge in production.

Budget accounting is durable and fails closed: an unreadable or unwritable ledger counts as unknown spend, Budget.check is only advisory, and a custom provider boundary needs its own scoped reserve and record calls around the real request. Authorization is checked before a journaled activity opens, so a later grant can still unblock a parked action. Model changes keep credentials out of canonical requests, resolving them just before transport, and live model tests need an explicit SMITHERS_LIVE_MODEL_TESTS flag rather than firing from ambient provider keys. Scheduled or webhook triggers need a durable idempotency key so retried claims are deduplicated.

When your agent uses it

  • Changing how Smithers resolves model seats, budgets or sandbox limits
  • Adding authorization checks around a journaled flow-call activity
  • Wiring a new completion evaluator or scorer into the agent loop
  • Debugging why a scheduled or webhook-triggered run double-fired

Example prompts

  • “Add a new credentialed model seat to the Smithers host configuration.”
  • “Why is Budget.check not actually blocking an over-budget flow call?”
  • “Add an idempotency key to this webhook trigger so retries don't double-run it.”

Requirements

  • The Smithers TypeScript workflow framework

What it can do on your machine

Read from SKILL.md and the folder at commit 25cb01d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Smithers Agent Runtime loads about 765 tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 353 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~765

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from smithersai/smithers at commit 25cb01d, republished under its MIT licence (© smithersai). 353 words, ~765 tokens.

Download SKILL.mdSave it as .claude/skills/smithers-agent-runtime/SKILL.md (or your agent's skills folder).
name
smithers-agent-runtime
description
Compose or change the Smithers agent loop, host services, model seats, budgets, sandbox limits, or flow-call authorization.

Smithers agent runtime

Read the agent composition guide and relevant package tests before changing host wiring or agent boundaries. Agent.Service owns one cell loop. Cells reach capabilities through ctx.call to ordinary flows; AgentSession and AgentAction adapt that same loop. A foreign CLI agent implements Agent.Service rather than adding a second loop.

The host resolves credentialed seats through SeatResolver, supplies quota and budget policy, and declares bounded sandbox limits. The completion evaluator is a host decision: select it before opening resources and refuse missing configuration rather than silently using a scripted or unavailable judge in production.

Budget accounting is durable. An unreadable or unwritable ledger is unknown spend and fails closed. Budget.check is advisory; a custom provider boundary needs scoped reserve and record around the real call. Check authorization before opening a journaled activity so a later grant can unblock a parked action. Keep the flow's declared capabilities and effects consistent with the bound implementation; verify recovery and refusal behavior in tests, not only a fresh run.

For model changes, read the model guide: canonical requests exclude credentials, which resolve just before transport. Ambient provider keys do not enable live tests; SMITHERS_LIVE_MODEL_TESTS=1 opts into quota-consuming calls. For command tools, read the Std guide: Bash hermetic is a lexical check, not OS confinement, and truncated output must stay visibly truncated. For scheduled or webhook launches, read the triggers guide: retryable claims require a durable idempotencyKey dedupe at RunnerService.start. For scoring receipts, read the scorers guide: a completed batch can contain inconclusive observations, and store failures are warnings; verify persistence by readback before claiming a grade was saved.

Show full SKILL.md (88 more words)Show less

For host capability composition, read the kernel guide. Replace the ordinary host service tags with their guarded implementations in place; a parallel protected service lets dependencies bypass the guard. Path is intentionally unchecked, so a path service alone is no confinement boundary.

For untrusted execution, read the sandbox provider guide and choose a provider whose documented boundary meets the threat model. The package itself adds no isolation; DirectorySandbox is a scratch directory with process lifecycle, not filesystem, user, or network confinement. Verify provider cancellation with its conformance suite.

© smithersai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/smithers-agent-runtime of smithersai/smithers.

Open the folder on GitHubat commit 25cb01d

Compare with similar skills

Smithers Agent Runtime next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Smithers Agent Runtime compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Smithers Agent Runtime this skillsmithersai/smithers430—~765Automated safety check: PassMIT
Show Me Your Work Decision Logcursor/plugins10k8 repos~1.6kAutomated safety check: PassNone
Nonstop Autonomous Modeandylizf/nonstop263—~2kAutomated safety check: WarnMIT
Loop FactoryJuliusBrussee/skills162—~2kAutomated safety check: PassMIT
Loop Architectfabricioctelles/skills106—~2.1kAutomated safety check: NotesMIT
Autonomous Agent Patternsdavila7/claude-code-templates32k7 repos~5.6kAutomated safety check: PassMIT

Similar skills

  • Show Me Your Work Decision Log

    cursor/plugins

    Official

    Keeps a TSV decision log for long or unattended agent runs, one row per decision with what, why, evidence and result, so a reviewer can check the work later.

    10k GitHub starsUsed in 8 repos~1.6k tokens
    Agent WorkflowsAuto-check passed

  • Nonstop Autonomous Mode

    andylizf/nonstop

    Lets Claude keep working while you are away, after a pre-flight that surfaces blockers, risky operations and open decisions, with a stop hook scoped to the session.

    263 GitHub stars~2k tokensUpdated 6 mo ago
    Agent WorkflowsAuto-check: warnings

  • Loop Factory

    JuliusBrussee/skills

    Run a spec-driven agent loop where coding tasks live as markdown specs that move through inbox → active → archive, get implemented by Claude Code or Codex, and pass a review gate before they count…

    162 GitHub stars~2k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

  • Loop Architect

    fabricioctelles/skills

    Design well-structured agent loops with best-practice coaching and cross-model review gates before you run them.

    106 GitHub stars~2.1k tokensUpdated 5 days ago
    Agent WorkflowsAuto-check: notes

  • Autonomous Agent Patterns

    davila7/claude-code-templates

    Design patterns for building autonomous coding agents. An agent skill from davila7/claude-code-templates.

    32k GitHub starsUsed in 7 repos~5.6k tokens
    Agent WorkflowsAuto-check passed

  • Hitl Protocol

    LeoYeAI/openclaw-master-skills

    HITL Protocol — the open standard for human decisions in autonomous agent workflows.

    2.2k GitHub stars~5.3k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed

More from smithersai/smithers

All 9 skills in this repo

  • Smithers Durable Flow Driver

    smithersai/smithers

    Runs or authors Smithers TypeScript flows for ordered agent stages with retries, approvals, bounded loops and crash-safe recovery, built from Flow.make, Action.make and Effect.

    430 GitHub stars~3k tokensUpdated today
    Auto-check passed

  • Smithers Flow Registry Internals

    smithersai/smithers

    Documents how Smithers discovers and registers workflow flow files, so catalog listings stay metadata-only while running a flow loads its full body and action layers.

    430 GitHub stars~432 tokensUpdated today
    Auto-check passed

  • Smithers Repository Maintenance

    smithersai/smithers

    Points agents to the right sources when changing the Smithers workspace graph, generated docs, benchmark and eval evidence, or durable flows in the Smithers repository.

    430 GitHub stars~2.3k tokensUpdated today
    Auto-check passed

  • flows-jj ABI Maintenance

    smithersai/smithers

    Procedure for changing or verifying the flows-jj native and WASM ABI, its committed artifact and its reproducibility campaign in the Smithers repository.

    430 GitHub stars~299 tokensUpdated today
    Auto-check passed

  • Smithers Chain

    smithersai/smithers

    Maintain the existing @smthrs/chain runner, journal replay, catalog handlers, or sandbox boundary.

    430 GitHub stars~299 tokensUpdated today
    Auto-check passed

  • Smithers Harness Detect

    smithersai/smithers

    Change local coding-harness discovery, account status, model flag detection, or version probes.

    430 GitHub stars~260 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Smithers Agent Runtime

What does Smithers Agent Runtime do?

Guides changes to the Smithers agent loop's host wiring: credentialed model seats, budget accounting, sandbox limits and flow-call authorization. Service owns a single cell loop and any foreign CLI agent should implement that interface rather than add a second loop. A host resolves credentialed seats through SeatResolver, supplies quota and budget policy, and declares bounded sandbox limits; the completion evaluator used to judge a run is a host decision that must be selected before resources open, refusing missing configuration rather than silently falling back to a scripted or unavailable judge in production.

When should I use Smithers Agent Runtime?

Smithers Agent Runtime fits situations like: changing how Smithers resolves model seats, budgets or sandbox limits; adding authorization checks around a journaled flow-call activity; wiring a new completion evaluator or scorer into the agent loop; debugging why a scheduled or webhook-triggered run double-fired.

How do I install Smithers Agent Runtime in Claude Code?

Run `npx skills add smithersai/smithers --skill smithers-agent-runtime -a claude-code`. Or copy the skill folder (.agents/skills/smithers-agent-runtime in smithersai/smithers) into .claude/skills/smithers-agent-runtime in your project. Claude Code loads it when a task matches its description.

How do I install Smithers Agent Runtime in Codex?

Run `npx skills add smithersai/smithers --skill smithers-agent-runtime -a codex`. Or copy the skill folder (.agents/skills/smithers-agent-runtime in smithersai/smithers) into .agents/skills/smithers-agent-runtime in your project. Codex loads it when a task matches its description.

Can I use Smithers Agent Runtime in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add smithersai/smithers --skill smithers-agent-runtime -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/smithers-agent-runtime, .gemini/skills/smithers-agent-runtime, .github/skills/smithers-agent-runtime and .opencode/skills/smithers-agent-runtime in your project.

What does Smithers Agent Runtime need to run?

SKILL.md names no scripts, command-line tools or credentials: Smithers Agent Runtime is instructions for the agent only. Our summary lists: The Smithers TypeScript workflow framework.

Does Smithers Agent Runtime access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Smithers Agent Runtime safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Smithers Agent Runtime use?

Smithers Agent Runtime is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Smithers Agent Runtime use?

About 765 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Smithers Agent Runtime?

Skills that share tags, products or a category with Smithers Agent Runtime: Show Me Your Work Decision Log (cursor/plugins, 10k stars), Nonstop Autonomous Mode (andylizf/nonstop, 263 stars), Loop Factory (JuliusBrussee/skills, 162 stars) and Loop Architect (fabricioctelles/skills, 106 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Smithers Agent Runtime?

smithersai (a GitHub organization) maintains it in smithersai/smithers, which has 430 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 9, 2026.

Source: smithersai/smithers on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.