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 yonatangross/orchestkit --skill autogit clone --depth 1 https://github.com/yonatangross/orchestkitWrote 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/yonatangross/orchestkit/auto)<a href="https://agentmods.dev/skills/yonatangross/orchestkit/auto"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/auto/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/yonatangross/orchestkit/auto"><img src="https://agentmods.dev/badge/skills/yonatangross/orchestkit/auto.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 15 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Excessive Agency · line 123 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00099 | $0.03498 |
| Opus 5.5 | $0.00040 | $0.01399 |
| Sonnet 5.5 | $0.00020 | $0.00700 |
| Haiku 4.5 | $0.00010 | $0.00350 |
Grade A, and why
auto 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 11d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
auto — Intent Router
The front door to OrchestKit. You describe a goal in plain English; the router classifies it and hands off to the right specialist. One entry point, many execution paths.
Why this exists: OrchestKit has 110 skills, but usage telemetry shows users fire only the handful they can name by memory (10 distinct skills across thousands of sessions). The dominant cause of "dead" skills is no front door — not low quality. This router turns "you must know the exact
/ork:<name>" into "describe what you want."
Core principle: routing is a deterministic workflow, not an autonomous agent (Anthropic, Building Effective Agents). Classify → confirm → hand off. The router never does the work itself — it picks who does.
When to use
By default, for any goal-shaped request. An unambiguous goal is a 1-step route: auto classifies, confirms in one line, and hands off — no extra hops, so there is no "too obvious for auto".
Use auto for… |
Skip only when… |
|---|---|
| Any goal description ("fix X", "get Y to Z") | Already executing inside another skill (no recursion) |
| The right skill isn't obvious | Chaining a known multi-skill workflow you're mid-way through |
| You think you know the skill — auto confirms & short-circuits |
Design note (2026-07-12): this table previously said "Go direct when you already know the skill / the request maps unambiguously to one". That inverted instruction made the front door structurally unreachable — a competent model always believes it knows the target, so the router recorded near-zero invocations across thousands of sessions (the exact dead-skill problem the "Why this exists" note above describes). Routers must be framed as the default path, not an escape hatch for confusion.
Intent categories → OrchestKit skill
| intent | signal words | routes to |
|---|---|---|
| fix | fix, debug, broken, failing, error, crash, regression | fix-issue |
| diagnose | why, why isn't, why does, why can't, investigate | fix-issue (investigation-first) |
| optimize | faster, reduce, latency, bundle, minimize, below N ms | a /goal optimization loop (see Gaps) |
| cover | coverage, untested, get to N% | cover --target N |
| e2e | e2e, in the browser, browser test, playwright | expect (run on the diff); cover when no e2e tests exist yet |
| design | design, architect, how should we, explore, idea | /ork:brainstorm |
| build | build, implement, create, add feature, from ticket | implement |
| review | review, PR, MR, pull request, #N | review-pr |
| verify | verify, check, make sure, passes, green | verify |
| improve-skill | improve the skill, optimize the prompt, SKILL.md | the holdout-promotion gate (see Gaps) |
| (fallback) | no confident category | clarify with ONE question |
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago Changed · +1 lines 5bc20412e68d
- 15d ago Changed · +1 lines 7be90e3ab666
- 21d ago Changed d71c3f05e07a
- 23d ago Changed e3112d15b99e
- 24d ago Changed · -1 lines e9a9b5e96217
- 27d ago Changed 130ba6684cb9
- 28d ago Changed e353dac44203
- 29d ago Changed 0564e53d9cb6
- 1mo ago Changed a6634f4c3ffc
- 1mo ago First seen · 192 lines · 99 tokens per session scan A 943a7421d5c2
auto is a skill published in the GitHub repository yonatangross/orchestkit (298 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 3,498 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
Agent Workflow Builder
Build multi-agent AI workflows with orchestration, tool use, and state management.
web-research
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research.
stall-reset
Reset CocoStall counters after an operator-approved recovery.
time-stepping
Plan and control time-step policies for transient simulations — couple CFL and physics-based stability limits with adaptive stepping, ramp initial transients through sharp gradients or phase changes, schedule output intervals and checkpoint cadence, and plan restart strategies for long-running jobs. Use when choosing…
system-tests
Generic, composable conventions for system tests — black-box tests exercising the running system from the outside through its public surface. Defines the stack-neutral contract (no internals, environment coordinates as configuration, test isolation, total verdict reporting) and the taxonomy of expectation origins…
device-control
Use when driving the user's Android device through devicecontrolstart, deviceui and deviceaction — opening apps, navigating screens, filling fields, or any multi-step flow through another app's UI.