Security · Addy Osmani
Security and Hardening by Addy Osmani
Hardens authentication, input handling, storage, integrations, and privacy boundaries.
Setup and compatibility
Part of Addy Osmani Agent Skills. The breadth creates more ceremony for small changes, and the collection is less like a single personal run than Matt’s. Teams should adopt its lifecycle intentionally instead of loading every skill without agreeing on checkpoints.
Editorial compatibility guidance: Claude Code · Codex · Cursor · Gemini CLI. This is not an executed compatibility test; see the review for source and run evidence.
Read Security and Hardening instructions and prerequisites · Read Addy Osmani Agent Skills setup documentation
Independent review
Security and Hardening widens an agent’s implementation lens to trust boundaries, untrusted input, sessions, data handling, external integrations, and privacy. It is one of the clearest capabilities Addy’s lifecycle adds beyond an inner-loop coding methodology.
Read the Security and Hardening review and usage guideTry this skill
Install · Individual skill
Run in a terminal from your target project. Requires Node.js 22.20+, npm/npx, Git and network access.
Single-skill installs omit shared checklists. Use the upstream integration or copy needed checklists into the skill’s references folder.
npx skills@latest add addyosmani/agent-skills --skill security-and-hardening -a claude-code
Command / route checked 30 October 2026. Upstream installationCLI optionsAgent support
Setup requirements and caveats
Run in a terminal from the target project. Requires Node.js 22.20+ (current skills CLI), npm/npx, Git and network access. Review the installer summary before confirming. Keeps this skill’s supporting files. Single-skill installation omits repository-level shared checklists. For supplementary references, use the upstream whole-repository integration or copy the needed checklists into the installed skill’s references folder.
These are documented requirements; installation has not been tested here.
Your agent needs its own account, runtime and model access. Usage charges depend on your plan; unrecorded costs are unknown.
Run the example
Start a fresh session in the target project. Provide the relevant files or diff. This is the review’s example request, not a record of your execution.
Use the security-and-hardening skill. Harden the document-sharing endpoint against authorization bypass, unsafe filenames, content-type confusion, and excessive retention.
Check your result · Successful first run
A prioritized threat assessment and bounded endpoint hardening with verification evidence.
Confirm the agent loaded the named skill, inspect the output and run the relevant checks. Installation alone does not prove a successful run.
Something not working?
The skill is missing from my agent
Check that the skill is installed for the selected agent and project/global scope. Open a fresh session in that project and check the agent’s skill list. Plugin installs may also need to be enabled.
The wrong skill runs, or nothing happens
Start a fresh conversation, explicitly name the skill using the request above, and provide the requested inputs. Ask the agent to confirm which skill it loaded. Check for duplicate installed copies or overlapping instructions.
The skill runs but the result is poor
Compare the result with the successful-first-run check above. Supply the missing files, reproduction steps or constraints, then ask for one focused correction. If the skill addresses a different problem, return to the task guide and compare alternatives.
Installation troubleshooting · missing dependencies
If npx fails, check the Node/npm versions in setup requirements, Git and network access. For skills CLI installs, run npx skills list (add -g for global). If a route changed, follow upstream instructions.
Collection background and tradeoffs
The breadth creates more ceremony for small changes, and the collection is less like a single personal run than Matt’s. Teams should adopt its lifecycle intentionally instead of loading every skill without agreeing on checkpoints.
Source maintained by Addy Osmani. Read original skill. Compatibility guidance and published showcase runs remain separate from your first run.