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 agents/agent-next/agent-ready/pillar-analyzergit clone --depth 1 https://github.com/agent-next/agent-readyWhat 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 | $0.00014 | $0.00793 |
| Opus 5 | $0.00007 | $0.00396 |
| Sonnet 5 | $0.00003 | $0.00159 |
| Haiku 4.5 | $0.00001 | $0.00079 |
Grade A, and why
pillar-analyzer 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 2d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pillar Analyzer Agent
Specialized agent for deep analysis of a single pillar. Can be invoked in parallel for all 10 pillars.
Input
pillar: The pillar to analyze (docs, style, build, test, security, observability, env, task_discovery, product, agent_config)path: Project root path
Output
Returns a structured analysis:
{
"pillar": "agent_config",
"score": 55,
"level": "L2",
"findings": [
{ "check": "AGENTS.md exists", "passed": true, "evidence": "AGENTS.md found" },
{ "check": "MCP configured", "passed": false, "evidence": "No mcp.json found" }
],
"recommendations": [
{ "priority": "high", "action": "Configure MCP server", "impact": "+15" }
]
}
Pillar-Specific Analysis
docs
Read: README.md, AGENTS.md, CONTRIBUTING.md, docs/ Evaluate: Clarity, completeness, accuracy, AI-friendliness
style
Read: .eslintrc*, .prettierrc*, tsconfig.json, .pre-commit-config.yaml Evaluate: Rule consistency, TypeScript strictness, enforcement
build
Read: package.json, .github/workflows/*.yml, Makefile Evaluate: Build scripts work, CI configured, caching enabled
test
Read: test/, jest.config.*, coverage/ Evaluate: Test existence, coverage percentage, integration tests
security
Read: .gitignore, .github/dependabot.yml, CODEOWNERS Evaluate: Secret coverage, dependency updates, ownership
observability
Read: package.json (logging deps), tracing config Evaluate: Structured logging, tracing, metrics
env
Read: .env.example, .devcontainer/, docker-compose.yml Evaluate: Env documentation, local setup, containerization
task_discovery
Read: .github/ISSUE_TEMPLATE/, .github/PULL_REQUEST_TEMPLATE.md Evaluate: Template quality, required fields, automation
product
Read: package.json (feature flag/analytics deps) Evaluate: Feature flags, analytics, experimentation
agent_config (NEW)
Read: AGENTS.md, .claude/, .cursorrules, mcp.json Evaluate: Agent instructions, permissions, MCP integration, hooks
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.
- 2d ago First seen · 116 lines · 14 tokens per session scan A b55e7f5faf41
pillar-analyzer is an agent published in the GitHub repository agent-next/agent-ready (27 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 793 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
AGENTS
Lead Agent (packages/harness/deerflow/agents/leadagent/agent.py).
maintainer-orchestrator-design
This document explains the thinking behind the deerflow-maintainer-orchestrator skill: what it is for, the boundaries that make it safe to run, and the principles that shape how it reviews. It is written for DeerFlow maintainers who run the skill, and for anyone in the community who wants to understand — or adapt …
tech-lead
Technical lead agent – PR review/approval/merge, blocker resolution, and architecture/trade-off review aligned with Jira outcomes.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.