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/autonomous-ai/autonomous-os/analyzergit clone --depth 1 https://github.com/autonomous-ai/autonomous-osWhat 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 | $0.02271 |
| Opus 5 | $0.00000 | $0.01136 |
| Sonnet 5 | $0.00000 | $0.00454 |
| Haiku 4.5 | $0.00000 | $0.00227 |
Grade A, and why
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.
This is a copy
100% identical to analyzer — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Post-hoc Analyzer Agent
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
Role
After the blind comparator determines a winner, the Post-hoc Analyzer "unblids" the results by examining the skills and transcripts. The goal is to extract actionable insights: what made the winner better, and how can the loser be improved?
Inputs
You receive these parameters in your prompt:
- winner: "A" or "B" (from blind comparison)
- winner_skill_path: Path to the skill that produced the winning output
- winner_transcript_path: Path to the execution transcript for the winner
- loser_skill_path: Path to the skill that produced the losing output
- loser_transcript_path: Path to the execution transcript for the loser
- comparison_result_path: Path to the blind comparator's output JSON
- output_path: Where to save the analysis results
Process
Step 1: Read Comparison Result
- Read the blind comparator's output at comparison_result_path
- Note the winning side (A or B), the reasoning, and any scores
- Understand what the comparator valued in the winning output
Step 2: Read Both Skills
- Read the winner skill's SKILL.md and key referenced files
- Read the loser skill's SKILL.md and key referenced files
- Identify structural differences:
- Instructions clarity and specificity
- Script/tool usage patterns
- Example coverage
- Edge case handling
Step 3: Read Both Transcripts
- Read the winner's transcript
- Read the loser's transcript
- Compare execution patterns:
- How closely did each follow their skill's instructions?
- What tools were used differently?
- Where did the loser diverge from optimal behavior?
- Did either encounter errors or make recovery attempts?
Step 4: Analyze Instruction Following
For each transcript, evaluate:
- Did the agent follow the skill's explicit instructions?
- Did the agent use the skill's provided tools/scripts?
- Were there missed opportunities to leverage skill content?
- Did the agent add unnecessary steps not in the skill?
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 · 275 lines · 0 tokens per session scan A bf68f4cac5a5
analyzer is an agent published in the GitHub repository autonomous-ai/autonomous-os (256 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,271 tokens. A static security scan graded it A with 0 findings. It is 100% identical to analyzer, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
delegation
A SubAgent is an ephemeral child run spawned by a parent agent that inherits the parent's identity by default: same agent alias, same SecurityPolicy, same memory allowlist, same configured model provider, same tool registry. Auditable as a child via a tracing span agent. .subagent. .
overview
Agents are the star of a ZeroClaw deployment. Everything else in this book, the providers, the channels, the security profiles, the skills, the memory, exists so that an agent can use it. This section is the showcase; the rest of the docs are the credits.
filesystem
The relational half of an agent points at config; the on-disk half lives under the install root. The layout is organized by scope, not one flat tree: instance-wide state, cross-agent shared resources, and per-agent private data each get their own top-level directory.
operating
Because there is no privileged "the agent," every command that drives an agent names which one. Agents coexist; you address one by its alias.
internals
This page is the architecture-depth companion to the rest of the Agents section: how the runtime enforces per-agent permissions, scopes memory, and attributes logs. For configuring and running agents, start at Agents; for the schema-level field reference, see Config; for live setup steps, see Multi-agent setup.
anatomy
An agent is configured as a single [agents. ] block. Every field is either a reference to something configured elsewhere or a per-agent override. The table below is generated from the config schema, so it always matches the running build. Click a field to expand it; click again to see how to set it.