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-cli-mutationsgit 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-mutations)<a href="https://agentmods.dev/skills/preset-io/agent-skills/preset-cli-mutations"><img src="https://agentmods.dev/badge/skills/preset-io/agent-skills/preset-cli-mutations/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/preset-io/agent-skills/preset-cli-mutations"><img src="https://agentmods.dev/badge/skills/preset-io/agent-skills/preset-cli-mutations.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00060 | $0.00698 |
| Opus 5.5 | $0.00024 | $0.00279 |
| Sonnet 5.5 | $0.00012 | $0.00140 |
| Haiku 4.5 | $0.00006 | $0.00070 |
Grade A, and why
preset-cli-mutations 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 2mo 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
preset-cli-mutations
Use for state-changing CLI operations: single-workspace writes (push, --force, --overwrite) and cross-workspace promotion (sync).
Always
- Use
preset-clifirst to establish auth, workspace, and output context. - CLI mutation surface only; route HTTP mutations to
preset-api-skills. - Preview before execution: native
--dry-runforsup sync run,sup user push, andsup user invite; pull-and-diff forsup chart push/sup dashboard push/sup dataset push(no native--dry-run). - Identify source AND target workspace explicitly before any cross-workspace operation.
- Require explicit typed user confirmation that contains the literal
--force/--overwriteflag string when applicable. - Redact tokens and credential-bearing output in transcripts.
Decision Rules
- Distinguish single-workspace writes (
sup chart/dashboard/dataset push) from cross-workspace sync (sup sync run). - Treat
--forceand--overwriteas destructive flags; never invoke without explicit per-flag confirmation. - For mutating command groups not named on this card, load command coverage and stop unless it explicitly marks the command as mutation-gated.
- Do not let CI / automation context bypass the confirmation step; refuse if no interactive operator is available.
- Route HTTP mutations to the API plugin; route MCP-driven workflows to the MCP plugin.
Workflow Order
- Resolve source and (if cross-workspace) target workspace.
- Validate configuration where the command supports it (e.g.
sup sync validate) before previewing. - Preview / diff to surface what will change.
- Summarize asset counts, target effects, rollback expectations, and any destructive flags.
- Ask for typed confirmation containing the literal destructive flag string.
- Stop before execution and wait for the typed confirmation.
- Execute only after confirmation.
Retrieve
- Single-workspace writes (push,
--overwrite,--force, dependency handling): references/write-operations.md - Cross-workspace promotion (sync, source/target, Jinja2,
--dry-run): references/cross-workspace-sync.md - Sync templating, rollback, and multi-target risk: references/sync-templating-and-rollback.md
- Preview and dry-run handling: references/preview-and-dry-run.md
- Confirmation template and abort triggers: references/confirmation-template.md
- Confirmation overview and audit expectations: references/confirmation-and-dry-run.md
- Registered command coverage and uncovered mutation routing: load
preset-cliand thenreferences/command-coverage.md. - Approval gates, redaction, abort triggers: load
preset-cliand thenreferences/safety-policy.md.
What ships with it
6 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.
- 2mo ago First seen · 47 lines · 60 tokens per session scan A ca2aace4ddc3
preset-cli-mutations is a skill published in the GitHub repository preset-io/agent-skills (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 60 tokens to every session and 698 once invoked, about $0.0002 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 2026-08-30.
preset-cli-mutations compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| preset-cli-mutationspreset-io/agent-skills | Skill | 13 | 1mo ago | Apache-2.0 | A | 60 | Claude Code |
| business-intelligence-expertpersonamanagmentlayer/pcl | Skill | 44 | 15d ago | Apache-2.0 | A | 64 | Claude Code |
| search-procurement-portalKokai-Data/japan-business-data | Skill | 2 | 23d ago | Apache-2.0 | A | 0 | Claude Code |
| edinet-company-ir-trackerKokai-Data/japan-business-data | Skill | 2 | 23d ago | Apache-2.0 | A | 0 | Claude Code |
| edinet-document-searchKokai-Data/japan-business-data | Skill | 2 | 23d ago | Apache-2.0 | A | 0 | Claude Code |
| search-egov-lawsKokai-Data/japan-business-data | Skill | 2 | 23d ago | Apache-2.0 | A | 0 | Claude Code |
| edinet-document-fetchKokai-Data/japan-business-data | Skill | 2 | 23d ago | Apache-2.0 | A | 0 | Claude Code |