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/swoelffel/claw-pilot/workspace-filesgit clone --depth 1 https://github.com/swoelffel/claw-pilotWrote 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/agents/swoelffel/claw-pilot/workspace-files)<a href="https://agentmods.dev/agents/swoelffel/claw-pilot/workspace-files"><img src="https://agentmods.dev/badge/agents/swoelffel/claw-pilot/workspace-files.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 5.1 | $0.00000 | $0.00910 |
| Opus 5 | $0.00000 | $0.00455 |
| Sonnet 5 | $0.00000 | $0.00182 |
| Haiku 4.5 | $0.00000 | $0.00091 |
Grade A, and why
workspace-files 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 6d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Workspace Files
Every agent in ClawPilot has a dedicated workspace directory containing files that shape its identity, behavior, team composition, and memory.
Standard Workspace Files
| File | Purpose | When Used |
|---|---|---|
SOUL.md |
Agent identity, capabilities, principles, personality | Injected into system prompt when promptMode=full |
AGENTS.md |
Team composition, communication links, delegation rules | Loaded at prompt build time for multi-agent awareness |
BOOTSTRAP.md |
First-contact guidance, onboarding instructions | Shown only on the very first message of a new session |
USER.md |
User preferences, custom instructions, working style | Injected into system prompt alongside SOUL.md |
HEARTBEAT.md |
Heartbeat check instructions, health verification steps | Read by the heartbeat scheduler at each check interval |
How Standard Files Are Loaded
The runtime reads workspace files during prompt construction. The loading order is:
- SOUL.md -- core identity block, always first
- USER.md -- user-specific overrides appended after SOUL
- AGENTS.md -- team topology for delegation-aware agents
- BOOTSTRAP.md -- conditional, only if
session.messageCount === 0
When promptMode is set to minimal, only SOUL.md summary lines are included to reduce token usage. Set promptMode=full for complete injection of all workspace content.
Custom Documentation Files
Any .md file placed in the docs/ subdirectory (or deeper) becomes part of the agent's knowledge base. Examples:
docs/reference/glossary.md-- terminology definitionsdocs/flows/daily-maintenance.md-- flow-specific instructionsdocs/security/authentication.md-- security context
Custom files are not injected into the system prompt automatically. They are accessed on demand through workspace search tools.
Workspace Knowledge Plugin
Agents equipped with the workspace-knowledge plugin gain two MCP tools:
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.
- 6d ago First seen · 105 lines · 0 tokens per session scan A 05208ce80af0
workspace-files is an agent published in the GitHub repository swoelffel/claw-pilot (10 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 910 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 2026-08-31.
Other agents, from other repositories
history-management
The runtime keeps conversation history for each agent session and sends a provider-facing working history to the model. Two complementary limits operate on different representations.
memory-keeper
Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that would help anyone starting with Claude on this project.
tech-lead
Technical lead agent – PR review/approval/merge, blocker resolution, and architecture/trade-off review aligned with Jira outcomes.
Explore
Fast read-only codebase & docs exploration. Returns structured findings, never raw file dumps.
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。.
universal
Paste this into your agent/LLM system instruction block.