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/fruafr/skills/incus-docnpx skills add fruafr/skills --skill incus-docgit clone --depth 1 https://github.com/fruafr/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/fruafr/skills/incus-doc)<a href="https://agentmods.dev/skills/fruafr/skills/incus-doc"><img src="https://agentmods.dev/badge/skills/fruafr/skills/incus-doc.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 | $0.00063 | $0.01605 |
| Opus 5 | $0.00032 | $0.00803 |
| Sonnet 5 | $0.00013 | $0.00321 |
| Haiku 4.5 | $0.00006 | $0.00161 |
Grade A, and why
incus-doc 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 6d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: incus-doc
- Purpose: Ground every Incus-related answer, command, and script in authoritative CLI help and documentation to eliminate hallucinations.
- Use when: The user asks a question about Incus, asks to write a script using incus CLI commands, asks to run incus commands, or any context where Incus is mentioned.
- Don't use when: The question is purely about general Linux/container concepts unrelated to Incus syntax or behavior.
- Success looks like: Every incus CLI invocation, flag, subcommand, and configuration option is verified against the skill's reference files before being emitted; no fabricated flags, subcommands, or behaviors.
Inputs
This skill does not require explicit inputs — it activates on context (incus mentions). The skill's own reference files serve as the input.
Assumptions:
- The
references/directory within the skill folder (incus-doc/references/) exists and is up to date. incus-doc/references/cli-help.mdcontains the authoritative list of all incus commands and subcommands with links to per-command help inincus-doc/references/cli/.incus-doc/references/cli-man.mdcontains the authoritative list of all incus man pages with links to per-command man pages inincus-doc/references/man/.incus-doc/references/docs/index.mdcontains the authoritative documentation tree with links to markdown files inincus-doc/references/docs/.
Output
Format: Grounded answer / corrected script / verified command
Every incus command, flag, or configuration option must be traceable to a reference file. If the reference does not contain the claim, the claim must not be emitted.
Reasoning
- Understand — Parse the user request; identify all incus commands, subcommands, flags, and configuration options.
- Plan — Determine which reference files to consult:
- Command/subcommand existence and flags →
incus-doc/references/cli-help.mdthenincus-doc/references/cli/<command>.txt - Man page lookup (man-page-style options, descriptions) →
incus-doc/references/cli-man.mdthenincus-doc/references/man/<command>.txt - Conceptual/configuration/documentation/REST API →
incus-doc/references/docs/index.mdthen relevant markdown file inincus-doc/references/docs/
- Command/subcommand existence and flags →
- Generate — Produce answer with every incus-specific element verified.
- Verify — Re-read relevant reference lines to confirm every flag, subcommand, and option exists.
What ships with it
60 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.
- LICENSE.txt 620 B
- README.md 3.4 KB
- references/cli-help.md 25 KB
- references/cli-man.md 2.9 KB
- references/cli/incus_admin_cluster.txt 581 B
- references/cli/incus_admin_init.txt 1.5 KB
- references/cli/incus_admin_recover.txt 914 B
- references/cli/incus_admin_shutdown.txt 987 B
- references/cli/incus_admin_sql.txt 1.7 KB
- references/cli/incus_admin_waitready.txt 803 B
- references/cli/incus_admin.txt 996 B
- references/cli/incus_cluster_add.txt 577 B
- references/cli/incus_cluster_edit.txt 697 B
- references/cli/incus_cluster_enable.txt 911 B
- references/cli/incus_cluster_evacuate.txt 709 B
- references/cli/incus_cluster_get.txt 642 B
- references/cli/incus_cluster_group_add.txt 586 B
- references/cli/incus_cluster_group_assign.txt 833 B
- references/cli/incus_cluster_group_create.txt 774 B
- references/cli/incus_cluster_group_delete.txt 589 B
- references/cli/incus_cluster_group_edit.txt 560 B
- references/cli/incus_cluster_group_list.txt 1.2 KB
- references/cli/incus_cluster_group_remove.txt 597 B
- references/cli/incus_cluster_group_rename.txt 600 B
- references/cli/incus_cluster_group_show.txt 573 B
- references/cli/incus_cluster_group.txt 1001 B
- references/cli/incus_cluster_info.txt 575 B
- references/cli/incus_cluster_list-tokens.txt 1.2 KB
- references/cli/incus_cluster_list.txt 1.2 KB
- references/cli/incus_cluster_remove.txt 720 B
- references/cli/incus_cluster_rename.txt 590 B
- references/cli/incus_cluster_restore.txt 624 B
- references/cli/incus_cluster_revoke-token.txt 577 B
- references/cli/incus_cluster_role_add.txt 583 B
- references/cli/incus_cluster_role_remove.txt 594 B
- references/cli/incus_cluster_role.txt 755 B
- references/cli/incus_cluster_set.txt 646 B
- references/cli/incus_cluster_show.txt 561 B
- references/cli/incus_cluster_unset.txt 643 B
- references/cli/incus_cluster_update-certificate.txt 693 B
- references/cli/incus_cluster.txt 1.6 KB
- references/cli/incus_config_device_add.txt 952 B
- references/cli/incus_config_device_get.txt 596 B
- references/cli/incus_config_device_list.txt 585 B
- references/cli/incus_config_device_override.txt 637 B
- references/cli/incus_config_device_remove.txt 603 B
- references/cli/incus_config_device_set.txt 752 B
- references/cli/incus_config_device_show.txt 573 B
- references/cli/incus_config_device_unset.txt 591 B
- references/cli/incus_config_device.txt 1.0 KB
- references/cli/incus_config_edit.txt 751 B
- references/cli/incus_config_get.txt 742 B
- references/cli/incus_config_metadata_edit.txt 575 B
- references/cli/incus_config_metadata_show.txt 575 B
- references/cli/incus_config_metadata.txt 770 B
- references/cli/incus_config_set.txt 1.0 KB
- references/cli/incus_config_show.txt 680 B
- references/cli/incus_config_template.txt 918 B
- references/cli/incus_config_trust_add-certificate.txt 984 B
- references/cli/incus_config_trust_add.txt 796 B
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.
- 6d ago First seen · 101 lines · 63 tokens per session scan A 842c573f6871
incus-doc is a skill published in the GitHub repository fruafr/skills (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 63 tokens to every session and 1,605 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 2026-08-31.
Other skills, from other repositories
datarobot-workload-api
Use when the user wants to create, configure, scale, debug, observe, or roll out container workloads on DataRobot's Workload API. Triggers include: deploying a container as a managed service, listing/starting/stopping workloads, changing replica counts or autoscaling, picking CPU/GPU compute bundles, injecting…
containers
Use when building or debugging container images. Covers multi-stage builds, layer caching, image size, non-root users, signal handling, and the security defaults most Dockerfiles get wrong.
kubernetes
Use when deploying to or debugging Kubernetes. Covers workload configuration, resource requests and limits, probes, rollout strategy, networking, and the failure modes that produce CrashLoopBackOff and OOMKilled.
dockerfile-best-practices
Create and optimize Dockerfiles and Compose files with BuildKit, multi-stage builds, cache mounts, and non-root hardening. Also triggers on container images, build performance, or Docker security, even without the word 'Dockerfile'.
helm-bjw-s-chart
Generate production-ready Helm charts on the bjw-s-labs common library (app-template v5, v4 legacy). Use for new charts, Compose-to-Helm conversion, sidecars, init containers, services, ingress, persistence, StatefulSets, HPAs, Service/PodMonitors, and NetworkPolicies.
speckit.devops
Docker Infrastructure & Security Hardening Specialist — Port ENV-first.