Borrowing it
Nothing to install: this file belongs to Nosmoht/talos-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Nosmoht/talos-mcp-server/main/.claude/skills/guard-mutating-tool/SKILL.mdgit clone --depth 1 https://github.com/Nosmoht/talos-mcp-serverWrote 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/nosmoht/talos-mcp-server/guard-mutating-tool)<a href="https://agentmods.dev/skills/nosmoht/talos-mcp-server/guard-mutating-tool"><img src="https://agentmods.dev/badge/skills/nosmoht/talos-mcp-server/guard-mutating-tool/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/nosmoht/talos-mcp-server/guard-mutating-tool"><img src="https://agentmods.dev/badge/skills/nosmoht/talos-mcp-server/guard-mutating-tool.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 | $0.00059 | $0.00950 |
| Opus 5.5 | $0.00024 | $0.00380 |
| Sonnet 5.5 | $0.00012 | $0.00190 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
guard-mutating-tool 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 1mo 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Guard Mutating Tool
Scan the current diff against the CLAUDE.md § Safety matrix (cached in
references/guard-matrix.md) and emit a structured report the
staff-reviewer agent can consume directly.
Arguments
Parse $ARGUMENTS:
--base <ref>— base ref for the diff. Defaults toorigin/main.
Validate the base ref:
git rev-parse --verify "${BASE:-origin/main}" >/dev/null \
|| abort "Unknown base ref: $BASE"
Key Steps
-
List changed mutating-tool files.
git diff --name-only "${BASE:-origin/main}"...HEAD -- 'internal/tools/*.go'Filter by basename to one of:
lifecycle,files,patch_blocklist, or any*_preflight(files that implementreboot,upgrade,rollback,reset,patch_config,apply_config, or preflight helpers that gate those mutations). Exit early with verdictGOif the filtered list is empty. -
Load the guard matrix. Read
references/guard-matrix.md. Itsrequired_argsanddefault_valuescolumns are the ground truth. -
Scan each file for guard presence. For every matched file:
git diff "${BASE:-origin/main}"...HEAD -U3 -- <file> \ | grep -nE 'confirm|nodes|dry_run|preserve|graceful|wait'Cross-reference the hunks against the matrix row for the tool.
-
Classify each guard. Flag a regression when:
- a required-arg check was removed (deletion of
if !confirm/len(nodes)==0), - a default literal changed (e.g.
dry_run: true→dry_run: false), - a new control-flow path reaches the mutating gRPC call without passing through the guard check.
- a required-arg check was removed (deletion of
4b. Preflight helper check. For any *_preflight.go in the filtered
set, load .claude/rules/quorum-member-counting.md and apply its
invariants against the diff (dedup by member Id before counting,
map[<id-type>]struct{} structure, no reliance on
len(msg.GetMembers())). Flag as regression if a preflight helper
is introduced or modified without the dedup pattern.
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.
- 1mo ago First seen · 93 lines · 59 tokens per session scan A a24db4d59fa5
guard-mutating-tool is a skill published in the GitHub repository Nosmoht/talos-mcp-server (4 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 950 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 2026-08-31.
Other skills, from other repositories
k8s
Operate the joelclaw Kubernetes cluster — Talos Linux on Colima (Mac Mini). Deploy services, check health, debug pods, recover from restarts, add ports, manage Helm releases, inspect logs, fix networking. Triggers on: 'kubectl', 'pods', 'deploy to k8s', 'cluster health', 'restart pod', 'helm install', 'talosctl'…
mirrord-prev-env
Help users create and manage mirrord preview environments — running a modified service as an isolated pod in a shared Kubernetes cluster, scoped by an environment key and HTTP/queue traffic filtering, so teams can validate and review changes against real traffic without affecting live services. Use when a developer…
mirrord-operator
Help users install and configure the mirrord Operator for team/enterprise environments. Use when users ask about operator setup, Helm installation, cloud API key or license configuration, air-gapped/offline licensing, enabling features (queue splitting, DB branching, preview environments, multi-cluster), internal…
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.
implementing-container-image-minimal-base-with-distroless
Reduce container attack surface by building application images on Google distroless base images that contain only the application runtime with no shell, package manager, or unnecessary OS utilities.
k8s-incident
Respond to Kubernetes incidents with runbooks and diagnostics. Use for outages, pod failures, node issues, network problems, and emergency response.