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 fledgeling-co/fledgeling-plugins --skill anvil-errandgit clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsWrote 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/fledgeling-co/fledgeling-plugins/anvil-errand)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/anvil-errand"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/anvil-errand.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 | $0.00232 | $0.01710 |
| Opus 5 | $0.00116 | $0.00855 |
| Sonnet 5 | $0.00046 | $0.00342 |
| Haiku 4.5 | $0.00023 | $0.00171 |
Grade A, and why
anvil-errand 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 today.
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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
anvil-errand
Run a Claude Code agent in a container on a machine that is not this one.
anvil errand is one name for a path whose pieces already existed and were
proved on hardware separately. The verb's own contribution is small and
specific: it asks whether every piece is in place before anything starts,
and when one is missing it says which, by a stable identifier, with the step
that fixes it.
That is the whole reason to prefer it over typing the underlying commands. The failure it removes is not "the errand did not work" — it is discovering the missing piece halfway through a container start, from a symptom that points somewhere else.
Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. Pastes the --check output and the refusal kind rather than describing them, reads docs/ERRAND_RUNBOOK.md before naming a next step, and caps retries so a refusal is answered rather than re-run. Other models skip it.
The loop
anvil errand --check # can this work? changes nothing
anvil errand -p "review /work/ and list the three worst bugs"
--check runs the preflight and stops. Everything after the verb is the
agent's own argv, appended to the image's entrypoint — so -p, --model,
--output-format stream-json --verbose and the rest reach Claude Code itself.
--check is positional and taken only immediately after the verb, so a prompt
that happens to contain the word (anvil errand -p "explain --check to me")
still runs.
Watch and stop it with the ordinary verbs — the errand is a normal job:
anvil ls # the job id
anvil attach <job-id> # its own stdout, streamed; read-only by design
anvil wait <job-id> # blocks, exits with the workload's own code
anvil stop <job-id>
anvil attach will not accept keystrokes and that is not a fault: the
container is started detached, so PID 1's stdin is at EOF from the first
instant. Use anvil exec <job-id> -- <cmd> to open a separate process beside
the agent.
What ships with it
1 file 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.
- today Changed 0248e67ba7a6
- 8d ago First seen · 121 lines · 232 tokens per session scan A 2f58b75a90d4
anvil-errand is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 232 tokens to every session and 1,710 once invoked, about $0.0012 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
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
implementing-rbac-hardening-for-kubernetes
Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.
docker-socket-mount
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.