Agent skill

Security Remediate

by cloudposse in cloudposse/atmos

Fix open Dependabot and CodeQL/code-scanning alerts directly on the current branch.

Apache-2.0Auto-check passedSecurity

Install Security Remediate

skills CLI
$ npx skills add cloudposse/atmos --skill security-remediate -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cloudposse/atmos security-remediate --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cloudposse/atmos.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/security-remediate .claude/skills/security-remediate && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
security-remediate
GitHub stars
1.4k
Token cost
~1.3k tokens
SKILL.md length
642 words
Files
1
Skills in repo
70
Repo updated
First seen
Licence
Apache-2.0

At a glance

Fix open Dependabot and CodeQL/code-scanning alerts directly on the current branch.

  • Works in 6 steps: Resolve context. → Query both alert sources live (the… → Filter to high-confidence fixes,… → …
  • PostToolUse hook after a git push where GitHub reports open vulnerabilities
  • SKILL.md covers Fork / permission prerequisite…, Workflow and What this skill must never do
  • Calls gh and make

What it does

Security Remediate is an agent skill from cloudposse/atmos. Fix open Dependabot and CodeQL/code-scanning alerts directly on the current branch. Triggered automatically by the security-remediate-trigger PostToolUse hook after a git push where GitHub reports open vulnerabilities; can also be invoked manually. Never opens a new PR or issue - commits land on the branch that's already open.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Security, covering Dependency management and Static analysis and SAST. It works with GitHub and Git. The repository describes itself as: Atmos is the open-source runtime for infrastructure — it builds, authenticates, and ships Terraform, OpenTofu, Packer, Ansible, Kubernetes, Helm, and containers the same way on… The licence is Apache-2.0.

When your agent uses it

  • PostToolUse hook after a git push where GitHub reports open vulnerabilities
  • Can also be invoked manually

Example prompts

  • “/security-remediate”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Resolve context.
  2. Query both alert sources live (the hook's cached alert set was only a trigger signal — treat it as stale)
  3. Filter to high-confidence fixes, following the precedent set by 0e32451913
  4. Apply fixes in the working tree, then verify before committing anything
  5. Commit directly onto the current branch. No new branch, no new PR, no issue — this branch already has an open PR, and the fix belongs on it
  6. Report a summary back in chat (not as a GitHub comment/issue): which alerts were fixed (numbers + URLs), and which weren't, with a reason…

What it can do on your machine

Read from SKILL.md and the folder at commit bbe58a6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh
    • make

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Security Remediate loads about 1.3k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 642 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~87
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from cloudposse/atmos at commit bbe58a6, republished under its Apache-2.0 licence (© cloudposse). 642 words, ~1,260 tokens.

Download SKILL.mdSave it as .claude/skills/security-remediate/SKILL.md (or your agent's skills folder).
name
security-remediate
description
Fix open Dependabot and CodeQL/code-scanning alerts directly on the current branch. Triggered automatically by the security-remediate-trigger PostToolUse hook after a git push where GitHub reports open vulnerabilities; can also be invoked manually. Never opens a new PR or issue - commits land on the branch that's already open.
metadata.copyright
Copyright Cloud Posse, LLC 2026
metadata.version
1.0.0

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

  1. Resolve context.

    bash
    owner_repo="$(gh repo view --json owner,name --jq '.owner.login + "/" + .name')"
    branch="$(git rev-parse --abbrev-ref HEAD)"
  2. Query both alert sources live (the hook's cached alert set was only a trigger signal — treat it as stale):

    bash
    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=open

    The -X GET is required: gh api implicitly sends a POST when -f/--paginate params are given without an explicit method, and these list endpoints 404 on POST — indistinguishable from a real permission error unless you notice the verb. If either call still 403/404s with -X GET present, stop and report the permission gap — do not proceed partway.

  3. Filter to high-confidence fixes, following the precedent set by 0e32451913:

    • Dependabot alerts: only fix if a patched version exists within what .github/dependabot.yml's ignore rules allow (that file currently ignores all major-version bumps across gomod, github-actions, and npm/website). If the only fix requires a major bump the policy blocks, do not bump it — report it as "blocked by dependabot ignore policy" instead.
    • CodeQL alerts: only fix rule IDs with an established safe pattern in this repo. Currently that's go/allocation-size-overflow, fixed by avoiding summed len() capacity hints (e.g., replacing make([]T, len(a)+len(b)) with a pattern that doesn't sum lengths as a capacity hint). Extend this list cautiously — an unfamiliar rule ID with an ambiguous fix goes in the "not auto-fixable" bucket, not a guessed fix.
    • GitHub Action pins: bump to the patched SHA/tag referenced by the alert.
    • npm/pnpm alerts (in website/): bump via pnpm.overrides in website/package.json, then regenerate NOTICE:
      bash
      go tool mage notice:generate
  4. Apply fixes in the working tree, then verify before committing anything:

    bash
    make lint
    go test ./... # or scope to the touched packages

    If either fails for a given fix, drop that fix from the commit and move it to the "not auto-fixable" report — don't commit something that doesn't pass.

  5. Commit directly onto the current branch. No new branch, no new PR, no issue — this branch already has an open PR, and the fix belongs on it:

    bash
    git add <only the files you actually changed>
    git commit -m "fix(security): remediate N CodeQL/Dependabot alerts"
  6. Report a summary back in chat (not as a GitHub comment/issue): which alerts were fixed (numbers + URLs), and which weren't, with a reason for each (major-bump blocked by policy, ambiguous/unfamiliar rule ID, no patch available yet, permission gap). Never silently drop an alert without accounting for it in this summary.

Show full SKILL.md (45 more words)Show less

What this skill must never do

  • Open a new pull request.
  • Open a new GitHub issue (per standing project guidance: never open issues without explicit per-issue user authorization).
  • Push past a dependabot.yml ignore rule.
  • Commit a fix that fails make lint or the targeted tests.

© cloudposse, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/security-remediate of cloudposse/atmos.

Open the folder on GitHubat commit bbe58a6

Compare with similar skills

Security Remediate next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Security Remediate compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Security Remediate this skillcloudposse/atmos1.4k—~1.3kAutomated safety check: PassApache-2.0
Security Vulnerabilities Patcheraxelixlabs/axelix147—~4.2kAutomated safety check: PassLGPL-3.0
Triaging Security Findingsbitwarden/ai-plugins154—~2.2kAutomated safety check: PassCustom licence
SkepticRaoFoundation/subtensor387—~660Automated safety check: PassApache-2.0
Sicurezza GitHubccplugins/awesome-claude-code-plugins967—~486Automated safety check: NotesApache-2.0
Clawsec ScannerLeoYeAI/openclaw-master-skills2.2k—~4.1kAutomated safety check: PassMIT

Similar skills

  • Create batched Dependabot-style pull requests for GitHub security findings in axelixlabs/axelix, grouped by dependency surface such as master/front-end, master/build.gradle.kts, or starter Gradle…

    147 GitHub stars~4.2k tokensUpdated yesterday
    SecurityAuto-check passed
  • Triaging Security Findings

    bitwarden/ai-plugins

    Official

    This skill should be used when the user asks to "triage security findings", "fix an Aikido finding", "review Aikido issues", "dismiss a false positive", "check SAST/IaC alerts", or needs to work…

    154 GitHub stars~2.2k tokensUpdated today
    SecurityAuto-check passed
  • Skeptic

    RaoFoundation/subtensor

    Run the security-focused Skeptic persona on the local working tree's diff against a base branch.

    387 GitHub stars~660 tokensUpdated today
    SecurityAuto-check passed
  • Sicurezza GitHub

    ccplugins/awesome-claude-code-plugins

    Aggiunge alle repository GitHub dei siti workflow di sicurezza automatici - scansione dipendenze vulnerabili, ricerca di segreti/chiavi nel codice, analisi statica CodeQL e Dependabot.

    967 GitHub stars~486 tokensUpdated 1 mo ago
    DevOps & CloudAuto-check: notes
  • Clawsec Scanner

    LeoYeAI/openclaw-master-skills

    Automated vulnerability scanner for agent platforms. An agent skill from LeoYeAI/openclaw-master-skills.

    2.2k GitHub stars~4.1k tokensUpdated 2 mo ago
    SecurityAuto-check passed
  • OBS Plugin Dependency Upgrade

    sorayuki/obs-multi-rtmp

    Updates the obs-multi-rtmp plugin repo to the latest upstream plugin template and OBS Studio version, including dependency metadata, then rebuilds it with CMake.

    5.1k GitHub stars~609 tokensUpdated 5 days ago
    DevelopmentAuto-check passed

More from cloudposse/atmos

All 70 skills in this repo
  • Fix Log

    cloudposse/atmos

    A skill your agent uses when implementing, finishing, documenting, or reviewing a fix, repair, remediation, bug fix, debug-and-fix task, workflow fix, infrastructure fix, or any change that should…

    1.4k GitHub stars~685 tokensUpdated today
    Auto-check passed
  • Atmos Lint

    cloudposse/atmos

    Atmos Terraform linting with TFLint: standalone atmos terraform lint, component-aware config discovery and toolchain versions, TFLint rule configuration, and lifecycle hooks/CI findings.

    1.4k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Changelog

    cloudposse/atmos

    Blog post authoring for Atmos: MDX template, frontmatter, website/blog/tags.yml and authors.yml rules, problem-first framing, backtick-opening ban, optional cast embeds, and no-Go-internals leakage.

    1.4k GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Editions

    cloudposse/atmos

    Decide whether a PR's new or changed default needs edition-journal handling (pkg/edition, docs/prd/editions.md), and do the mechanical work if so: journal entries, the four-layer default check…

    1.4k GitHub stars~2.1k tokensUpdated today
    Auto-check passed
  • Atmos Migration

    cloudposse/atmos

    Migrate to Atmos from native Terraform, Terraform Workspaces, Terramate, Terragrunt, Make, Just, or Task; migrate tool versions from mise or Aqua CLI; migrate AWS/GCP/Azure CLI configs, Leapp…

    1.4k GitHub stars~5.1k tokensUpdated today
    Auto-check: warnings
  • PR Maintenance Loop

    cloudposse/atmos

    Start an hourly background loop that keeps the current branch's PR rebased, its addressed CodeRabbit threads resolved, its CI checks passing, its lint clean, its tests passing with adequate patch…

    1.4k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Works with

Questions about Security Remediate

What does Security Remediate do?

Fix open Dependabot and CodeQL/code-scanning alerts directly on the current branch. Security Remediate is an agent skill from cloudposse/atmos. Fix open Dependabot and CodeQL/code-scanning alerts directly on the current branch.

When should I use Security Remediate?

Security Remediate fits situations like: postToolUse hook after a git push where GitHub reports open vulnerabilities; can also be invoked manually.

How do I install Security Remediate in Claude Code?

Run `npx skills add cloudposse/atmos --skill security-remediate -a claude-code`. Or copy the skill folder (.claude/skills/security-remediate in cloudposse/atmos) into .claude/skills/security-remediate in your project. Claude Code loads it when a task matches its description.

How do I install Security Remediate in Codex?

Run `npx skills add cloudposse/atmos --skill security-remediate -a codex`. Or copy the skill folder (.claude/skills/security-remediate in cloudposse/atmos) into .agents/skills/security-remediate in your project. Codex loads it when a task matches its description.

Can I use Security Remediate in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cloudposse/atmos --skill security-remediate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/security-remediate, .gemini/skills/security-remediate, .github/skills/security-remediate and .opencode/skills/security-remediate in your project.

What does Security Remediate need to run?

Going by SKILL.md and its folder, Security Remediate needs the command-line tools its instructions call (gh and make).

Does Security Remediate access the network?

SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Security Remediate safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Security Remediate use?

Security Remediate is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Security Remediate use?

About 1.3k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Security Remediate?

Skills that share tags, products or a category with Security Remediate: Security Vulnerabilities Patcher (axelixlabs/axelix, 147 stars), Triaging Security Findings (bitwarden/ai-plugins, 154 stars), Skeptic (RaoFoundation/subtensor, 387 stars) and Sicurezza GitHub (ccplugins/awesome-claude-code-plugins, 967 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Security Remediate?

cloudposse (a GitHub organization) maintains it in cloudposse/atmos, which has 1,395 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on October 7, 2026.

Source: cloudposse/atmos on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.