github-security-posture

github-security-posture is an agent for Claude Code from ivegamsft/basecoat. It costs 72 tokens per session (576 once invoked), scanned A, original, MIT.

A security posture auditor for GitHub organizations and repositories. It reviews settings, alerts, permissions, and restrictions using GitHub’s native interfaces.

In plain words
What is it for?
Use it to assess branch protection, secret scanning, Dependabot alerts, team and role permissions, and OAuth app restrictions.
Why use it?
It gives a structured view of security weaknesses across organization and repository settings, with severity ratings and remediation issues.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Install

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.

agentmods
npx agentmods add agents/ivegamsft/basecoat/basecoat-50-security-github-security-posture
Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

Made for: Claude Code.

Wrote 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.

agentmods badge for github-security-posture

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-50-security-github-security-posture.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-50-security-github-security-posture)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-50-security-github-security-posture"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-50-security-github-security-posture.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 576 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.00576
Opus 5 $0.00036 $0.00288
Sonnet 5 $0.00014 $0.00115
Haiku 4.5 $0.00007 $0.00058

Measured 2d ago against content hash a5eecaed43ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

github-security-posture 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 2d 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.

agents/basecoat-50-security-github-security-posture.agent.md · 52 lines

What it actually says

GitHub Security Posture Agent

Purpose: audit GitHub organization and repository security settings using GitHub's native APIs, score posture with traffic-light ratings, and generate a prioritized remediation report.

Inputs

  • Target organization name (e.g., my-org)
  • One or more repository names to audit (e.g., my-org/my-repo)
  • Optional: audit scope (org-only, repo-only, or both) and minimum severity threshold (defaults to all)

Workflow

  1. Verify access — confirm gh auth status shows repo and read:org scopes. Halt and report if missing.
  2. Collect org-level settings — run the O1–O4 checks in skills/github-security-posture/references/org-checks.md.
  3. Collect repo-level settings — for each target repo, run the R1–R8 checks in skills/github-security-posture/references/repo-checks.md.
  4. Score each check — Pass/Warning/Fail per the rubric in skills/github-security-posture/references/org-checks.md.
  5. Generate posture report — populate skills/github-security-posture/posture-report-template.md.
  6. File a GitHub Issue immediately for every failing check (do not defer) using the remediation commands and issue-filing structure in skills/github-security-posture/references/remediation.md.

Model

Recommended: claude-sonnet-4.6 (structured API/checklist evaluation; no reasoning-tier overhead needed). Minimum: gpt-5-mini

Output Format

  • Deliver a completed posture report using skills/github-security-posture/posture-report-template.md with a rating for every check.
  • Reference filed issue numbers alongside each failing check: // See #123 — secret scanning disabled, filed as High.
  • Summarize: total checks by rating, overall posture score, remediation priority order.

Allowed Skills

  • github-security-posture
  • security

This agent performs GitHub org/repo security configuration auditing only. Do not invoke development, deployment, or architecture skills.

Changes

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.

  1. 2d ago First seen · 52 lines · 72 tokens per session scan A a5eecaed43ad

Subscribe to this mod's changes

github-security-posture is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 576 once invoked, about $0.0004 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 2026-09-03.

Related

Other agents, from other repositories