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/cloudposse/atmos/security-remediatenpx skills add cloudposse/atmos --skill security-remediategit clone --depth 1 https://github.com/cloudposse/atmosWrote 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/cloudposse/atmos/security-remediate)<a href="https://agentmods.dev/skills/cloudposse/atmos/security-remediate"><img src="https://agentmods.dev/badge/skills/cloudposse/atmos/security-remediate.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 | $0.00070 | $0.01213 |
| Opus 5 | $0.00035 | $0.00607 |
| Sonnet 5 | $0.00014 | $0.00243 |
| Haiku 4.5 | $0.00007 | $0.00121 |
Grade A, and why
security-remediate 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 yesterday.
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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Remediate (Atmos)
Proactively fix GitHub-reported security alerts on the branch you're already working on, instead of letting them accumulate until a manual sweep (see commit 0e32451913 for what that manual sweep looked like).
Fork / permission prerequisite (read first)
This repo is public, so a plain gh token with repo scope (the default from gh auth login) is sufficient to read both alert endpoints — security_events is only required on private repos (see GitHub's Dependabot alerts API docs: private repos need security_events, public repos only need public_repo/repo). Don't chase a security_events scope refresh for this repo; it's unnecessary and, per cli/cli#12073 and independent reports (e.g. microsoft/sarif-sdk#3081), gh auth refresh -s security_events can report success while GitHub silently drops the scope anyway — a dead end that's easy to mistake for a real permission gap.
If gh api calls below still 404/403 even with -X GET present, that's a genuine permission gap (e.g. a fork contributor without repo access, or a future private-repo use of this skill lacking security_events) — stop and report it instead of attempting a workaround. .claude/hooks/security-remediate-trigger.sh treats that case exactly like "no alerts open" and silently does nothing.
Workflow
-
Resolve context.
owner_repo="$(gh repo view --json owner,name --jq '.owner.login + "/" + .name')" branch="$(git rev-parse --abbrev-ref HEAD)" -
Query both alert sources live (the hook's cached alert set was only a trigger signal — treat it as stale):
gh api "repos/${owner_repo}/dependabot/alerts" -X GET --paginate -f state=open gh api "repos/${owner_repo}/code-scanning/alerts" -X GET --paginate -f state=openThe
-X GETis required:gh apiimplicitly sends aPOSTwhen-f/--paginateparams are given without an explicit method, and these list endpoints 404 onPOST— indistinguishable from a real permission error unless you notice the verb. If either call still 403/404s with-X GETpresent, stop and report the permission gap — do not proceed partway.
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.
- yesterday Changed a6d3dbaf6213
- 3d ago First seen · 68 lines · 70 tokens per session scan A 41da5589bf84
security-remediate is a skill published in the GitHub repository cloudposse/atmos (1,369 stars, last pushed today), licensed Apache-2.0. It adds 70 tokens to every session and 1,213 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
nvca-self-managed-install
Install or validate the NVCA Operator chart against a self-managed NVCF control plane from the native monorepo. Use when the control plane comes from deploy/stacks/self-managed and NVCA must be installed with stack-derived image repository settings.
obol-stack
Monitor the Kubernetes cluster running the Obol Stack. Use when asked about pod status, logs, services, events, deployments, or diagnosing issues. Read-only access to own namespace via ServiceAccount.
architecture
Java 21 | Spring Boot 4.0.2 | Kubernetes Client 25.0.0 | Picocli 4.7.6.
helm-upstream
Check latest Helm releases for issues and fixes applicable to jhelm.
kubeview-debug
Debug and diagnose Kubernetes clusters using KubeView MCP server tools. Use when investigating cluster issues (pod crashes, deployment failures, service connectivity problems, node issues, resource constraints), performing cluster health checks, or troubleshooting any Kubernetes workload. Trigger phrases include…
bazel-k8s-expert
Expert knowledge for deploying Quarkus/Java applications to Kubernetes using Bazel. Covers rulesk8s, Helm, Kustomize, ConfigMaps, Secrets, and health probes.