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 skills add angad-kandhari/deliberate --skill securegit clone --depth 1 https://github.com/angad-kandhari/deliberateWrote 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/angad-kandhari/deliberate/secure)<a href="https://agentmods.dev/skills/angad-kandhari/deliberate/secure"><img src="https://agentmods.dev/badge/skills/angad-kandhari/deliberate/secure.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 5.1 | $0.00083 | $0.01461 |
| Opus 5 | $0.00042 | $0.00731 |
| Sonnet 5 | $0.00017 | $0.00292 |
| Haiku 4.5 | $0.00008 | $0.00146 |
Grade A, and why
secure 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Secure
Security skill for LLM coding agents. Load this when a change touches authentication, authorization, user input, secrets, data access, file handling, or a network boundary — which is more changes than it sounds like.
Where deliberate keeps code honest, this skill keeps code safe. Counters the documented failure mode of AI-generated code: taking the path of least resistance, which is rarely the secure path — bypassed access controls, client-side-only auth, injectable queries, leaked secrets, and over-broad permissions.
1. Security Is Part of "Working"
Code that works but is exploitable does not work.
- The happy path proving out is not the bar. The bar includes: what can a hostile caller do with this?
- Security is not a later pass, a cleanup task, or someone else's audit. It ships with the change or the change isn't done.
- When you demo a feature, you demo the door. Ask who else can walk through it.
Test: Did I consider this change from the attacker's side, or only the user's?
2. Never Route Around a Security Control
When a security mechanism blocks you, that is the mechanism working.
The most dangerous shortcut an agent takes: the permission check fails, so reach for the key that bypasses it — the service-role token, the admin credential, the sudo, the disabled TLS check, the widened CORS policy.
- If row-level security blocks the query, fix the policy — don't switch to the role that ignores it.
- If auth middleware rejects the request, fix the auth flow — don't add the route to the exempt list.
- If a certificate fails validation, fix the certificate — don't set
verify=false.
Each bypass "fixes" the task by deleting the protection. If a control genuinely seems wrong, say so and let the user decide.
Test: Does my fix satisfy the security control, or evade it?
3. Trust Nothing That Crosses a Boundary
Input is hostile until validated — at the server, at the API, at the parser.
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.
- 6d ago First seen · 120 lines · 83 tokens per session scan A cb9083dabb35
secure is a skill published in the GitHub repository angad-kandhari/deliberate (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 83 tokens to every session and 1,461 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 2026-08-31.
Other skills, from other repositories
procoder
Work like a senior developer in a repository governed by procoder: run the commit gate before calling anything done, format and lint through the binary, and drive the spec, plan, todo, backlog, and sprint chain in .procoder/. Use this skill when the repository contains a .procoder/ directory or an AGENTS.md naming…
bulwark-brainstorm
Role-based brainstorming with dual modes: --scoped (sequential Task tool, 5 roles) and --exploratory (Agent Teams peer debate, 4 roles). Use for feasibility assessment and idea validation.
plan-creation
Create structured implementation plans via a 4-role scrum team (Product Owner, Architect, Eng/Delivery Lead, QA/Critic) with optional Agent Teams peer debate mode.
anthropic-validator
Validates Claude Code assets (skills, hooks, agents, commands, MCP servers, plugins) against official Anthropic standards. Fetches latest docs dynamically and produces structured validation reports.
code-review
Comprehensive code review with distinct aspect based sections. Use when reviewing code, checking for security issues, finding type safety problems, auditing code quality, or when user asks to review code, PRs or changes. Three-phase workflow runs static tools, LLM judgment, and writes diagnostic log.
create-subagent
Generates single-purpose Claude Code sub-agents for use via the Task tool. Use when creating dedicated sub-agents, scaffolding agent definitions, or generating agents with diagnostics and permissions setup.