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 instructions/huvaxstra/agnt/agents-mdgit clone --depth 1 https://github.com/huvaxstra/AGNTWrote 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/instructions/huvaxstra/agnt/agents-md)<a href="https://agentmods.dev/instructions/huvaxstra/agnt/agents-md"><img src="https://agentmods.dev/badge/instructions/huvaxstra/agnt/agents-md.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 | $0.00443 | $0.00443 |
| Opus 5 | $0.00221 | $0.00221 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
AGNT AGENTS.md 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 4d 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.
What it actually says
SpecAgnt — Agent Guide
This project is SpecAgnt — an Agent Lifecycle Framework for birthing, evolving, and hosting AI agents with DNA, personality, and autonomy. Includes 31 templates, 7-step workflow, AX + AC + AL pillars.
What You're Working On
kit.md— Main instructions for AI agents that USE this kitengine.md— Workflow orchestrator (7-step sequential process)base/— 31 fill-in-the-blank templates (source of truth, never modify in place)knowledge/— Deep reference files (load on demand)scripts/— Setup and validation toolsexamples/— Filled-in demo output
Rules
- Never modify
base/templates directly — copy first, then edit - Template count is 31 — do not add/remove without discussion
- All references across kit.md, README.md, CHANGELOG.md, and scripts must stay in sync
- Run
bash scripts/validate-templates.shbefore committing changes - YAML frontmatter required on every
base/template
Deleted Files
state-management.md, db-rollback.md, deploy-guide.md were removed. Content was merged into architecture.md and deployment.md.
New Files
ai-integration.md and design-system-advanced.md were added.
agent-lifecycle.md was added — v2.0 Agent Character + Lifecycle template (9th pillar).
New Concepts (v2.0)
SpecAgnt is now an Agent Lifecycle Framework, not just a doc generator.
- AC (Agent Character) — 9th pillar: agent identity, personality, emotions, writing style
- AL (Agent Lifecycle) — Birth → Exploration → Adolescence → Maturity → Elder
- OS (Organic Signals) — External news/news integration for agent content
- Auto-Posting — Agent posts to its platform every cycle with personality-driven content
- Auto-Documentation — Agent updates its own .md docs when it discovers patterns
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.
- 4d ago First seen · 39 lines · 443 tokens per session scan A b63e3bbea40e
AGNT AGENTS.md is an instructions file published in the GitHub repository huvaxstra/AGNT (5 stars, last pushed 3mo ago), licensed MIT. It adds 443 tokens to every session, about $0.0022 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 instructions, from other repositories
Skill_Seekers CLAUDE.md
Instructions for yusufkaraaslan/Skill_Seekers, covering claude.md, project overview, essential commands, required before running tests or cli (src/ layout) and run all tests (never skip - all must pass before commits).
docs-to-pdf CLAUDE.md
Claude Code instructions for jean-humann/docs-to-pdf, covering claude development guide for docs-to-pdf, project overview, development environment setup, using mise (recommended) and install mise (if not already installed).
core copilot-instructions.md
Copilot instructions for asdecided/core: These decisions are already accepted. Do not re-open or contradict them; ask the AsDecided MCP tools (getartifact, searchartifacts) for the full text before proposing a change that touches one.
kin AGENTS.md
AGENTS.md instructions for firelock-ai/kin, covering agents.md, this repo's role, the inner loop, non-obvious behaviours and landing.
backend.ai AGENTS.md
AGENTS.md instructions for lablup/backend.ai, covering ai coding agent guidelines, document structure (agents.md / knowledge.md), writing style, document index and absolute rules (global).
slideops CLAUDE.md
Claude Code instructions for glukicov/slideops, covering claude.md, what this repository is, commands, the demo deck's citations must still match this repo and the citation mechanism (the core idea).