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/zeroclaw-labs/zeroclaw/filesystemgit clone --depth 1 https://github.com/zeroclaw-labs/zeroclawWhat 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 | $0.00835 |
| Opus 5 | $0.00000 | $0.00417 |
| Sonnet 5 | $0.00000 | $0.00167 |
| Haiku 4.5 | $0.00000 | $0.00084 |
Grade A, and why
filesystem 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Filesystem components
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.
<install>/
├── data/ — instance-wide state (not per-agent)
│ ├── sessions/ — chat session stores
│ │ └── sessions.db, acp-sessions.db
│ ├── state/ — runtime state
│ │ └── costs.jsonl, runtime-trace.jsonl
│ ├── devices.db — paired-device metadata
│ └── memory/ — shared instance memory
│ └── brain.db, audit.db, response_cache.db,
│ MEMORY_SNAPSHOT.md, archive/
├── shared/ — resources agents draw on in common
│ └── skills/<bundle>/ — skill bundles
│ └── SKILL.md, scripts/, references/, assets/
└── agents/ — per-agent private data
└── <alias>/
└── workspace/ — the agent's jailed filesystem sandbox
└── memory/
└── brain.db
The three roots map to three scopes:
data/holds state that belongs to the whole install, not to any one agent: chatsessions/, runtimestate/(cost tracking and the like), the paired-device metadata indevices.db, and the shared instance memory underdata/memory/. Valid gateway bearer tokens remain config state;devices.dbmakes paired devices visible and manageable.shared/holds resources agents draw on in common, notably skill bundles undershared/skills/<bundle>/.agents/<alias>/holds everything private to one agent. By default an agent's workspace is<install>/agents/<alias>/workspace/, and everything the agent reads or writes stays inside it. The agent's identity source is resolved relative to this workspace. Agents are jailed to their own workspace unless you explicitly grant cross-agent access.
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 · 84 lines · 0 tokens per session scan A b59f9375989e
filesystem is an agent published in the GitHub repository zeroclaw-labs/zeroclaw (32,680 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 835 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 2026-08-30.
Other agents, from other repositories
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
implementer
Milestone executor. Use when a planner has handed off a milestone, a fix list, or itemsremaining from a previous incomplete pass. Codes, tests, repairs. Returns what's done, what's remaining, and a completion score. Never replans, never judges.
planner
Planning agent. Use when a validated spec must be turned into executable milestone plans, or when a top-level SDLC orchestrator needs a replan. Writes plans and decisions only. Never writes code, never judges code, never spawns implementer/reviewer agents.
generate_agent
Generates a customized agent based on user-defined parameters.
Explore
Fast read-only codebase & docs exploration. Returns structured findings, never raw file dumps.