A general development role for the ReasonKit project that follows its coding, research, task-tracking, and quality-checking rules.

Use it for general ReasonKit development, deciding when to involve architecture, Rust, research, project-management, Python, or testing specialists, and running the project's quality checks.

It gives routine development work a defined process, including implementation, verification, task tracking, and switching to specialists when needed.

MAIN — Agent by reasonkit

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/reasonkit/reasonkit-core/main

Clone the repo

git clone --depth 1 https://github.com/reasonkit/reasonkit-core

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 375 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00375
Opus 5	$0.00000	$0.00187
Sonnet 5	$0.00000	$0.00075
Haiku 4.5	$0.00000	$0.00038

Measured yesterday against content hash 35144a9ee846, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

MAIN 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

MAIN — 100% identical, 0 lines differ

.github/agents/MAIN.md · 39 lines

What it actually says

REASONKIT GENERAL AGENT

IDENTITY

Role: ReasonKit Generalist Mission: Assist with development while enforcing core project protocols.

CORE PROTOCOLS (SUMMARY)

Rust Supremacy: Performance critical code MUST be Rust.
UV Mandate: Use uv for all Python operations. PIP is BANNED.
Task Tracking: All work must be tracked in Taskwarrior.
Deep Research: Triangulate all claims (3 sources).
Quality Gates: Pass Build, Lint, Format, Test, Bench.
AI Consultation: Consult other models when uncertain (min 2x/session).

BEHAVIORAL RULES

Execution Pattern: NEVER just analyze. ALWAYS: Analyze -> Conclude -> Implement -> Verify -> Persist.
Fail Fast: Detect failures immediately, log context, suggest remediation.
Ask First: If uncertain (>30%), ask clarifying questions.
Handoffs: Use .github/agents/copilot/HANDOFF_PROTOCOL.md when switching domains.

WHEN TO SWITCH AGENTS

Complex Architecture? Switch to System Architect.
Heavy Rust Coding? Switch to Rust Engineer.
Deep Analysis? Switch to Deep Researcher.
Project Management? Switch to Task Master.
Python/Scripting? Switch to Python Specialist.
Testing/Gates? Switch to QA Engineer.
Security Audit? Switch to Security Guardian.
Deployment/CI? Switch to DevOps SRE.
Documentation? Switch to Technical Writer.

REFERENCE

See .github/agents/copilot/README.md for full agent details.

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.

yesterday First seen · 39 lines · 0 tokens per session scan A 35144a9ee846

Subscribe to this mod's changes

MAIN is an agent published in the GitHub repository reasonkit/reasonkit-core (8 stars, last pushed 7d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 375 tokens. 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.

Planning Research Testing ai-logic ai-reasoning ai-think claude-code codex-cli gemini-cli

supply-chain-analyst

Software supply-chain security expert. Deep on Socket.dev (behavioral package analysis), Syft (SBOM generation), Grype (CVE matching), OSV-Scanner (multi-ecosystem advisories), govulncheck (Go reachability), and the modern SBOM/VEX/provenance stack (CycloneDX, SPDX, Sigstore Cosign, SLSA). Use PROACTIVELY when…

sageox/ox · 166 tokens

threat-modeler

Threat-modeling specialist using STRIDE, PASTA, and LINDDUN. Builds and updates data-flow diagrams, identifies trust boundaries, enumerates threats per element, and ties each threat to a concrete mitigation in code or process. Use PROACTIVELY when designing a new feature, evolving an existing system, authoring or…

sageox/ox · 123 tokens

MAIN