Tools

Every open-source repository by Muhammad Basit Ali, with one line on what it does and the command to install or run it. Each name links to the project page.

Claude Code skill packs

claude-skills

Every skill I maintain, in one repository: 87 skills in 13 plugins from the packs below, one marketplace, one install script, synced daily.

/plugin marketplace add basitalisandhu/claude-skills
/plugin install aws-security@claude-skills

Claude Code skills for ways of working: change requests from a Terraform plan, an action ledger across meeting notes, exception and risk registers, RFC lint, a decision log, weekly status notes, a private 1:1 ledger and focus time from a calendar export.

No install step: see the README.

aws-security-skills

AWS security skills for Claude Code: account audit, SCP guardrails, blast-radius landing zones, IAM least privilege, Security Hub triage.

/plugin marketplace add basitalisandhu/aws-security-skills
/plugin install aws-security@aws-security-skills

repo-engineering-skills

Repository engineering skills for Claude Code: docs checked against the code, audits where every finding cites a line, agent context files that say only what code cannot.

docker run --rm -v "$PWD:/work" ghcr.io/basitalisandhu/repo-engineering-skills:0.4.1 docs-truth /work --only-failures
docker run --rm -v "$PWD:/work" ghcr.io/basitalisandhu/repo-engineering-skills:0.4.1 readme-check /work/README.md
docker run --rm -v "$PWD:/work" ghcr.io/basitalisandhu/repo-engineering-skills:0.4.1 test-gaps /work --top 20
docker run --rm -v "$PWD:/work" ghcr.io/basitalisandhu/repo-engineering-skills:0.4.1 hygiene /work --sarif /work/hygiene.sarif
docker run --rm ghcr.io/basitalisandhu/repo-engineering-skills:0.4.1 --help

m365-governance-skills

Microsoft 365 governance skills for Claude Code: Entra ID posture review, Intune baseline check, Graph permission preflight, Teams and group sprawl, access review pack.

claude plugin marketplace add basitalisandhu/m365-governance-skills
claude plugin install m365-governance@m365-governance-skills --scope user

compliance-evidence-skills

Compliance evidence skills for Claude Code: integrity-checked evidence packs from GitHub, AWS and Microsoft 365 exports, mapped to ISO 27001 and SOC 2, with narratives that cite evidence or say not assessable.

python3 plugins/compliance-evidence/skills/evidence-pack-builder/scripts/evidence_pack.py build tests/fixtures/exports --out /tmp/pack
python3 plugins/compliance-evidence/skills/evidence-pack-builder/scripts/evidence_pack.py verify tests/fixtures/evidence-pack/tampered-pack
python3 plugins/compliance-evidence/skills/control-map-from-exports/scripts/control_map.py /tmp/pack --framework iso27001 \
  --map plugins/compliance-evidence/skills/control-map-from-exports/references/starter-map.yaml --out /tmp/control-map.json
python3 plugins/compliance-evidence/skills/auditor-narrative-drafter/scripts/narrative.py /tmp/control-map.json --control A.8.15
python3 plugins/compliance-evidence/skills/github-change-control-evidence/scripts/github_evidence.py tests/fixtures/github/free-plan

claude-dev-skills

Claude Code skills for everyday development: code review, refactoring, debugging, CI and containers, data and APIs, documentation and security basics.

/plugin marketplace add basitalisandhu/claude-dev-skills
/plugin install code-quality@claude-dev-skills

agent-security-skills

Claude Code security plugin and agent skills for securing LLM agents: threat modelling, configuration audits, prompt injection review, MCP server review, incident lookup.

/plugin marketplace add basitalisandhu/agent-security-skills
/plugin install agent-security@agent-security-skills

github-manager-skills

Claude Code skills for engineering managers that compute from exported GitHub data: stuck-PR and review-queue digest, iteration report, blameless postmortem timeline.

No install step: see the README.

mac-maintenance-skills

Claude Code skills for cleaning up and speeding up a Mac: read-only survey first, safe tier removes only what programs recreate, leftovers and duplicate finders.

No install step: see the README.

claude-code-tooling-skills

Claude Code skills for keeping a Claude Code setup safe: review a third-party skill before installing it, lint skill descriptions, audit the context budget, build least-privilege permissions, test hooks.

No install step: see the README.

agent-identity-governance-skills

Claude Code skills for agent identity governance: inventory the non-human identities agents run as, review permissions, recertify quarterly, catch expiring credentials, switch one off fast.

No install step: see the README.

MCP tooling

dev-mcp-servers

Ten small MCP servers for everyday development and security checks.

claude mcp add jwt-tools -- docker run --rm -i ghcr.io/basitalisandhu/mcp-jwt-tools:0.2.1
claude mcp list

mcp-server-template

Secure MCP server template in TypeScript and Python, safe by default.

cd typescript
npm ci && npm run build && npm test
MCP_ALLOWED_DIRS=$PWD/../docs node dist/index.js        # stdio server exposing one directory

mcp-tools-lint

Lint MCP tool schemas and annotations before clients reject them.

npx @basitalisandhu/mcp-tools-lint --help              # run without installing
npm install -g @basitalisandhu/mcp-tools-lint@0.2.0    # global CLI, installs the mcp-tools-lint command
npm install -D @basitalisandhu/mcp-tools-lint@0.2.0    # as a dev dependency of a server project

mcp-auth-doctor

Diagnose OAuth discovery problems on remote MCP servers.

pipx install git+https://github.com/basitalisandhu/mcp-auth-doctor
mcp-auth-doctor https://your-server.example.com/mcp      # read-only; add -v for evidence
mcp-auth-doctor https://your-server.example.com/mcp --json > report.json

mcp-egress

Record every host an MCP server contacts, per tool, and fail CI on new ones.

pipx install git+https://github.com/basitalisandhu/mcp-egress                       # isolated CLI install
uvx --from git+https://github.com/basitalisandhu/mcp-egress mcp-egress --help       # run without installing
pip install git+https://github.com/basitalisandhu/mcp-egress                        # into the current environment
git clone https://github.com/basitalisandhu/mcp-egress && cd mcp-egress && uv venv && uv pip install -e ".[dev]"   # development

claude-mcp-allow

Least-privilege Claude Code permission rules for MCP tools, generated from their annotations.

npx @basitalisandhu/claude-mcp-allow            # print the proposed rules, change nothing
npx @basitalisandhu/claude-mcp-allow --diff --write
npx @basitalisandhu/claude-mcp-allow --check    # later, or in CI: exit 1 on drift

agentdojo-mcp

Run the AgentDojo benchmark's user and injection tasks against a real MCP server's tools.

pip install "agentdojo-mcp[dojo] @ git+https://github.com/basitalisandhu/agentdojo-mcp"

# 1. What does the server offer?
agentdojo-mcp inspect --stdio "python my_server.py" --json -o tools.json

# 2. Propose a mapping for a suite, then edit it.
agentdojo-mcp map --suite travel --server-dump tools.json -o mapping.yaml
agentdojo-mcp validate-mapping mapping.yaml --suite travel --server-dump tools.json

# 3. Check the mapping with the reference solutions first (no model, no network).
agentdojo-mcp run --suite travel --mapping mapping.yaml --stdio "python my_server.py" \
  --model ground-truth --attack direct

# 4. Run a model. Keys come from the environment variables AgentDojo and the provider SDKs read.
agentdojo-mcp run --suite travel --mapping mapping.yaml --stdio "python my_server.py" \
  --model provider:model-name --attack important_instructions --tasks user_task_0 --tasks user_task_1
# ... see the README for the rest

garak-mcp-probes

Run garak against your own MCP servers, with detectors for denied tool calls, leaked canaries and runaway step counts.

garak-mcp doctor --dry-run
garak-mcp run --dry-run --probes test.Test --report-dir garak-mcp-report

mcp-rc-check

MCP specification migration checker for the 2026-07-28 revision: flags removed, changed and deprecated constructs and writes a patch for mechanical fixes.

git clone https://github.com/basitalisandhu/mcp-rc-check && cd mcp-rc-check && npm ci && npm run build
node dist/cli.js scan --stdio "node /path/to/your/server.js"   # or --url https://host/mcp, or --dump file.json
node dist/cli.js scan --dump test/fixtures/fixture-pre-revision.json   # try it on a bundled pre-revision dump

Security tooling

agent-off-switch

Find every AI agent identity in Microsoft 365, AWS and GitHub, see what it can reach, and switch it off. Offline on saved exports.

pip install "git+https://github.com/basitalisandhu/agent-off-switch@v0.1.0"
aos --help

skill-scan-gate

CI gate for Claude Code skills and plugins, with SARIF output. GitHub Action and CLI.

pip install skill-scan-gate

agent-threat-model

Threat modeling for AI agents: describe the system in YAML, get a STRIDE and OWASP Agentic threat model.

pipx install git+https://github.com/basitalisandhu/agent-threat-model
atm init system.yaml                 # writes the support-bot example
atm analyse system.yaml

agent-config-audit

Audit AI agent configuration files for security risks.

pipx install git+https://github.com/basitalisandhu/agent-config-audit
cd your-project
agent-config-audit --fail-on high

agentic-semgrep-rules

Semgrep rules for AI agent code in Python, TypeScript and JavaScript.

pip install semgrep

# the single-file bundle, straight from GitHub (Semgrep accepts a URL only for a single file)
semgrep --config https://raw.githubusercontent.com/basitalisandhu/agentic-semgrep-rules/main/agentic-semgrep-rules.yaml .

# or the rules directory from a clone
git clone https://github.com/basitalisandhu/agentic-semgrep-rules
semgrep --config agentic-semgrep-rules/rules .

security-actions

GitHub Actions for AI agent and supply chain security checks.

name: security-actions
on:
  push:
    branches: [main]
  pull_request:
permissions:
  contents: read
  security-events: write
jobs:
  checks:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v7
      - uses: basitalisandhu/security-actions/agent-config-audit@v0
      - uses: basitalisandhu/security-actions/prompt-secrets-scan@v0
      - uses: basitalisandhu/security-actions/license-audit@v0
# ... see the README for the rest

cc-hooks

Typed Python SDK and offline test runner for Claude Code hooks.

pipx install git+https://github.com/basitalisandhu/cc-hooks   # the cc-hooks command (see "Install" for the library side)
python3 -m pip install git+https://github.com/basitalisandhu/cc-hooks   # the library, for the python3 that runs your hooks

cc-plugin-lock

Lock file for Claude Code plugins: pins plugins and skills to content hashes and verifies them before load.

pipx install git+https://github.com/basitalisandhu/cc-plugin-lock

# 1. Lock what is installed now (review your plugins first; the lock records what you trust).
cc-plugin-lock lock -o ~/.claude/cc-plugins.lock.json --store

# 2. Any time later: has anything changed?
cc-plugin-lock verify --lock ~/.claude/cc-plugins.lock.json

# 3. Gate every session: print the hook block and merge it into ~/.claude/settings.json.
cc-plugin-lock hook --lock ~/.claude/cc-plugins.lock.json

claude-perm-sim

Claude Code permission rule simulator: shows which rule decides a tool call and where a rule set is permissive.

npx github:basitalisandhu/claude-perm-sim load                               # effective rules, with the file each came from
npx github:basitalisandhu/claude-perm-sim explain "Bash(git push origin main)"  # which rule decides one call
npx github:basitalisandhu/claude-perm-sim bypass                             # where an allow rule admits more than it names

llms-txt-gen

Generate llms.txt for any docs site or repository.

pipx install git+https://github.com/basitalisandhu/llms-txt-gen

llms-txt-gen generate docs/ --out llms.txt --base-url https://docs.example.com
llms-txt-gen generate https://docs.example.com/sitemap.xml --out llms.txt --full
llms-txt-gen check llms.txt
llms-txt-gen serve-snippet

scp-guardrails

Build AWS service control policies from a short spec and lint them for lockouts and statements that deny nothing.

pip install scp-guardrails                                                              # once published to PyPI
pipx install git+https://github.com/basitalisandhu/scp-guardrails                        # the scp-guardrails command, isolated
uvx --from git+https://github.com/basitalisandhu/scp-guardrails scp-guardrails --help   # run without installing

spotlighting

Spotlighting for prompt injection defence in Python: mark untrusted text before it reaches a model.

pipx install git+https://github.com/basitalisandhu/spotlighting            # the spotlighting command
python3 -m pip install git+https://github.com/basitalisandhu/spotlighting  # the library

Tools

Claude Code skill packs

MCP tooling

Security tooling

Data and lists