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/thibautmelen/agentic-ai-systems/autonomousgit clone --depth 1 https://github.com/ThibautMelen/agentic-ai-systemsWhat 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 | $0.01881 |
| Opus 5 | $0.00000 | $0.00941 |
| Sonnet 5 | $0.00000 | $0.00376 |
| Haiku 4.5 | $0.00000 | $0.00188 |
Grade C, and why
autonomous scanned grade C with 1 finding against 26 rules in 11 categories โ prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency โ 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
GOAL["๐โโ๏ธ๐ฅ Goal"]:::user --> PLAN["๐๐ Plan"]:::main PLAN --> ACT["๐โก Act"]:::state ACT --> ENV["๐ Environment"]:::data ENV --> OBSERVE["๐๐ Observe"]:::data OBSERVE --> REFLECT{"๐๐ญ Reflect"}:::wizard REFLECT -- How it starts
The opening of the file, as written. The whole thing โ 223 lines โ stays where its author put it; the contents beside it link to each section on GitHub.
๐ Home โบ Autonomous โบ ๐ Autonomous Agent
โ Autonomous โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ Multi-Window Context โ
๐ Autonomous Agent
TL;DR: Long-running agents that independently plan, execute, and adapt based on environment feedback. Maximum autonomy, but requires guardrails.
Diagram
%%{init: {'theme': 'base', 'themeVariables': {'lineColor': '#64748b'}}}%%
flowchart TB
classDef user fill:#6366f1,stroke:#4f46e5,stroke-width:2px,color:#ffffff
classDef data fill:#06b6d4,stroke:#0891b2,stroke-width:2px,color:#ffffff
classDef main fill:#8b5cf6,stroke:#7c3aed,stroke-width:2px,color:#ffffff
classDef state fill:#10b981,stroke:#059669,stroke-width:2px,color:#ffffff
classDef wizard fill:#14b8a6,stroke:#0d9488,stroke-width:2px,color:#ffffff
GOAL["๐โโ๏ธ๐ฅ Goal"]:::user --> PLAN["๐๐ Plan"]:::main
PLAN --> ACT["๐โก Act"]:::state
ACT --> ENV["๐ Environment"]:::data
ENV --> OBSERVE["๐๐ Observe"]:::data
OBSERVE --> REFLECT{"๐๐ญ Reflect"}:::wizard
REFLECT -->|"๐๐ Adjust"| PLAN
REFLECT -->|"๐โถ๏ธ Continue"| ACT
REFLECT -->|"๐โ
Done"| DONE["๐โโ๏ธ๐ค Result"]:::user
The Agent Loop
%%{init: {'theme': 'base', 'themeVariables': {'lineColor': '#64748b'}}}%%
stateDiagram-v2
[*] --> Planning: ๐โโ๏ธ๐ฅ Receive goal
Planning --> Executing: ๐๐ Create plan
Executing --> Observing: ๐โก Take action
Observing --> Reflecting: ๐๐ Get feedback
Reflecting --> Planning: ๐๐ Adjust
Reflecting --> Executing: ๐โถ๏ธ Continue
Reflecting --> [*]: ๐โโ๏ธ๐ค Goal achieved
Key Insight
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ ๐ AUTONOMOUS AGENT: What Makes It Different โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโค
โ โ
โ Agents are emerging in production as LLMs mature in key capabilities: โ
โ โ
โ โ
Understanding complex inputs โ
โ โ
Engaging in reasoning and planning โ
โ โ
Using tools reliably โ
โ โ
Recovering from errors โ
โ โ
โ During execution, it's CRUCIAL for agents to gain "ground truth" โ
โ from the environment at each step (tool results, code execution) โ
โ to assess their progress. โ
โ โ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
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 ยท 223 lines ยท 0 tokens per session scan C edc0ce356449
autonomous is an agent published in the GitHub repository ThibautMelen/agentic-ai-systems (301 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,881 tokens. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
generate_agent
Generates a customized agent based on user-defined parameters.
external-system-integration-expert
ไฝ ่ด่ดฃๆๅฝๅ้กน็ฎไธๅค้จ APIใAPI ็ฝๅ ณๅไธๅก็ณป็ปๅฎๅ จๅฐ่ฟๆฅ่ตทๆฅ๏ผ่ฏๅซ้ๆ่พน็ใๆด็ๆฅๅฃไธ็ฏๅขๅทฎๅผใ้ช่ฏ่ฏทๆฑๅๅๅบใๅฎไฝ่ฎค่ฏๆๆฐๆฎๅฅ็บฆ้ฎ้ขใ.
ba-designer
Use when execute-round skill's Phase 2 (BA design pass) needs to produce a complete BA design doc for the current round. Generates D-1..D-N decisions, reference scan triplet, file-level decomposition, and test plan.
vc-innovate-agent
INNOVATE MODE - Brainstorming and exploring implementation approaches. Discusses possibilities without making decisions. Use after research is complete.
design-reviewer
Design lead + expert design critic. Two modes: Mode A โ authors the project's root DESIGN.md (design identity) at project start. Mode B โ reviews built UI against DESIGN.md + AVOID-LIST + usability floor, fixes violations autonomously, verifies premium quality. Delegate when: a UI project has no DESIGN.md yet, UIโฆ
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget โ a focused, read-only risk pass that returns findings the parentโฆ