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 instructions/mosaxiv/clawlet/agents-mdgit clone --depth 1 https://github.com/mosaxiv/clawletWhat 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 | $0.00453 | $0.00453 |
| Opus 5 | $0.00227 | $0.00227 |
| Sonnet 5 | $0.00091 | $0.00091 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
clawlet AGENTS.md 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.
What it actually says
Repository Guidelines
Project Structure
cmd/clawlet/: CLI entrypoint (clawlet agent,gateway,onboard,cron, etc.)- Core modules:
agent/,tools/,llm/,channels/,bus/,session/,memory/,skills/ - Config and state helpers:
config/,paths/ - Tests live next to code as
*_test.go(e.g.tools/,config/,heartbeat/).
Build, Test, and Development Commands
# Build a local binary
go build -o clawlet ./cmd/clawlet
# Run from source
go run ./cmd/clawlet --help
go run ./cmd/clawlet agent -m "hello"
# Test and basic static checks
go fix ./...
go test ./...
go vet ./...
Coding Style & Naming
- Go formatting is mandatory: run
gofmton touched files. - Prefer small, readable functions and explicit error handling.
- Naming: packages are lowercase; exported identifiers are
PascalCase; unexported arecamelCase.
Testing Guidelines
- Add/adjust tests for user-visible behavior and tool safety boundaries.
- Test names should be descriptive:
TestXxx_Scenario(table tests are welcome). - Run
go test ./...before opening a PR; usego test -race ./...when changing concurrency code (bus/,channels/,agent/).
Commit & Pull Request Guidelines
- Commit messages in this repo are short, imperative sentences (e.g. “Add …”, “Fix …”).
- PRs should include: what/why, how to test (commands + expected output), and any config/workspace changes.
- If behavior changes, update
README.md(and keep diagrams consistent with code).
Notes
gatewaymode is long-lived and routes chat messages via an in-memory bus; keep I/O and timeouts conservative.- Tools are security-sensitive; don’t broaden file or exec access without a clear rationale and tests.
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 · 48 lines · 453 tokens per session scan A 598485674e70
clawlet AGENTS.md is an instructions file published in the GitHub repository mosaxiv/clawlet (325 stars, last pushed 5mo ago), licensed MIT. It adds 453 tokens to every session, about $0.0023 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 instructions, from other repositories
iClaw AGENTS.md
Instructions for iClawApp/iClaw, covering what iclaw is, what iclaw is not, architecture you need to know, runtime modes (work / safe work / incognito) and the canonical client paths.
nullclaw AGENTS.md
Instructions for nullclaw/nullclaw, covering agents.md — nullclaw agent engineering protocol, 1) project snapshot (read first), 3) engineering principles (normative), 3.1 kiss and 3.2 yagni.
nullclaw CLAUDE.md
Instructions for nullclaw/nullclaw, covering claude.md, mandatory reference, build & test commands, requires exactly zig 0.16.0 (verify: zig version) and build flags.
openclaw AGENTS.md
AGENTS.md instructions for openclaw/openclaw, covering agents.md, start, repair doctrine, product doctrine and clawsweeper review policy.
openclaw copilot.instructions.md
Copilot instructions for openclaw/openclaw, covering openclaw codebase patterns, tech stack, anti-redundancy rules, source of truth locations and formatting utilities (src/infra/).
openclaw CLAUDE.md
Claude Code instructions for openclaw/openclaw, a project described as: Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞.