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 agentmods add skills/angad-kandhari/deliberate/explorenpx skills add angad-kandhari/deliberate --skill exploregit 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/explore)<a href="https://agentmods.dev/skills/angad-kandhari/deliberate/explore"><img src="https://agentmods.dev/badge/skills/angad-kandhari/deliberate/explore.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 | $0.00075 | $0.01288 |
| Opus 5 | $0.00037 | $0.00644 |
| Sonnet 5 | $0.00015 | $0.00258 |
| Haiku 4.5 | $0.00007 | $0.00129 |
Grade A, and why
explore 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 5d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explore
Codebase-familiarity skill for LLM coding agents. Load this when working in a codebase you didn't write — which for an agent is every codebase — before adding code to it.
Where deliberate governs how to write and architect governs where code belongs, this skill governs what to learn first. Counters the failure mode behind AI-era duplication data: changes that look fine in isolation but ignore the system — re-implemented helpers, pattern-blind additions, and edits to files the agent never read.
Scale the depth to the task: a one-line fix needs the surrounding function; a new feature needs the neighborhood.
1. Read Before You Write
Never edit a file you haven't read. Never call code you haven't looked at.
- Read the whole file you're changing, not just the hunk. The convention you're about to violate is usually 40 lines up.
- Read the functions you call and the callers of what you change. Signatures lie by omission; behavior lives in the body.
- Read the nearest test file. Tests are the executable documentation of intent.
Editing on the basis of a filename and a grep hit is how orthogonal breakage happens.
Test: Have I actually read every file this diff touches, top to bottom?
2. Search Before You Create
The helper you're about to write probably exists. Find it first.
Duplication is the signature failure of generated code — the same function re-implemented in three files because nobody looked. Before writing anything reusable-shaped:
- Search for the name you'd give it, and the names this codebase would give it.
- Search for the operation itself: the regex, the API call, the transformation.
- Check the utils/helpers/lib modules and the closest sibling feature.
- Found something close? Extend or reuse it. Only write new when you can say why the existing one doesn't fit.
Test: Can I name the search I ran to confirm this doesn't already exist?
3. Find the House Style and Match It
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.
- 5d ago First seen · 115 lines · 75 tokens per session scan A befd2bb78107
explore is a skill published in the GitHub repository angad-kandhari/deliberate (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 75 tokens to every session and 1,288 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.
test-audit
Audit test suites for T1-T4 violations using AST analysis, mock detection, and multi-stage synthesis. Invoke when user asks to audit tests, check test quality, find mock violations, review test effectiveness, or inspect test suites for over-mocking. Triggers automatic rewrites when quality gates fail.
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.