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 preset-io/agent-skills --skill preset-cligit clone --depth 1 https://github.com/preset-io/agent-skillsWrote 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/preset-io/agent-skills/preset-cli)<a href="https://agentmods.dev/skills/preset-io/agent-skills/preset-cli"><img src="https://agentmods.dev/badge/skills/preset-io/agent-skills/preset-cli.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 | $0.00058 | $0.00768 |
| Opus 5 | $0.00029 | $0.00384 |
| Sonnet 5 | $0.00012 | $0.00154 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade A, and why
preset-cli 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 8d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
preset-cli
Use as the foundation for shell, scripting, CI/CD, and agent-driven Preset workflows through the sup CLI.
Always
- CLI surface only; stay on MCP or direct API if that's what the user requested.
- Default to
--jsonfor automation and agent consumption. - Keep
SUP_PRESET_API_TOKEN/SUP_PRESET_API_SECRETout of command lines and shared output; use env vars orsup config auth, never paste secrets on the command line. - Route push, sync, overwrite, and
--forcetopreset-cli-mutations. - Redact tokens and credential-bearing output in transcripts.
Decision Rules
- Classify CLI vs MCP vs direct API intent before acting; if MCP or direct API was requested, defer to that plugin.
- Run metadata reads and explicitly requested data-returning reads (e.g.
sup sql,sup chart data) on familiar workspaces directly with bounded output; forsup sql, this direct path requires a pure single-statementSELECT. Load safety policy before mutations, SQL that is not a pure single-statementSELECT, untrusted-source SQL, unfamiliar workspaces, or broad outputs. - Choose output format based on the downstream consumer:
--jsonfor automation,--csvfor files, default Rich for humans,--porcelainfor shell pipelines. - If a command group is not named on this card, load command coverage before composing commands.
- For mutating intent, stop and load
preset-cli-mutationsrather than continuing on this card. Non-SELECTSQL is confirmation-gated by the safety policy even when it is pasted by the user for a familiar workspace.
Workflow Order
- Establish install, auth, and workspace context.
- Choose output format.
- Classify risk (metadata read vs data-returning read vs mutation).
- Load the focused reference for the operation.
- Run only the safe / read command.
- Redact output before sharing.
Retrieve
- Install, entry points, OAuth, env vars: references/install-and-auth.md
- Config precedence and source resolution: references/config-precedence.md
- Workspace selection and
--workspace-idoverride: references/workspace-and-config.md - Registered command coverage and routing: references/command-coverage.md
- Output formats and exit behavior: references/output-formats.md
- Asset read/export entity scope: references/assets-read.md
- Asset list filter matrix: references/asset-filter-matrix.md
- Ad-hoc SQL routing: references/sql-and-query.md
- SQL/data-returning read safety: references/sql-data-safety.md
- Saved query reads: references/saved-query-reads.md
- Detailed command examples: references/command-examples.md
- CLI vs API routing decision: references/cli-vs-api.md
- Approval gates and credential redaction: references/safety-policy.md
What ships with it
13 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.
- references/asset-filter-matrix.md 1.3 KB
- references/assets-read.md 2.5 KB
- references/cli-vs-api.md 3.2 KB
- references/command-coverage.md 5.0 KB
- references/command-examples.md 786 B
- references/config-precedence.md 1.7 KB
- references/install-and-auth.md 3.0 KB
- references/output-formats.md 2.6 KB
- references/safety-policy.md 5.2 KB
- references/saved-query-reads.md 758 B
- references/sql-and-query.md 2.4 KB
- references/sql-data-safety.md 2.0 KB
- references/workspace-and-config.md 3.5 KB
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.
- 8d ago First seen · 50 lines · 58 tokens per session scan A 8a87a6e7a364
preset-cli is a skill published in the GitHub repository preset-io/agent-skills (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 768 once invoked, about $0.0003 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
autonomous-loops
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.
deployment-pipeline-design
Design multi-stage CI/CD pipelines with approval gates, security checks, and deployment orchestration. Use this skill when designing zero-downtime deployment pipelines, implementing canary rollout strategies, setting up multi-environment promotion workflows, or debugging failed deployment gates in CI/CD.
gitlab-ci-patterns
Build GitLab CI/CD pipelines with multi-stage workflows, caching, and distributed runners for scalable automation. Use when implementing GitLab CI/CD, optimizing pipeline performance, or setting up automated testing and deployment.
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.