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/sign-protocol/sign-tools/agents-mdgit clone --depth 1 https://github.com/sign-protocol/sign-toolsWhat 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 | $0.00686 | $0.00686 |
| Opus 5 | $0.00343 | $0.00343 |
| Sonnet 5 | $0.00137 | $0.00137 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
sign-tools 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Sign Tools Toolbox
This repository is a monorepo for tools supporting the SIGN-LANG project. It uses an agentic development operating system to enable AI-assisted implementation while maintaining human control over strategy and risk.
Repository Purpose
Sign Tools is a curated collection of reference implementations for the SIGN-LANG ecosystem:
- Document converters (sign-ingest)
- Utilities and integrations (TBD)
- Shared code and schemas
Each tool is independently versioned, tested, and documented but shares repo-wide coordination.
Start Here
Read these files in order:
README.md- Repository overview.agent/SOUL.md- Engineering posture.agent/policies/approvals.md- Approval boundaries.agent/policies/agent-coding-standards.md- Code standards.agent/operating-system/README.md- Operating system.agent/operating-system/product/README.md- Current mission
Tool Onboarding
For tool authors adding a new tool to the toolbox:
- Create
packages/<tool-name>/directory - Create tool-specific README and SPECIFICATION
- Follow repo-wide coding standards
- Implement tool-specific tests and validation
- Document in root README.md
For contributors to existing tools:
- Find the tool in
packages/ - Follow its README and SPECIFICATION
- Refer to repo-wide policies for standards and approvals
- Create tool-specific plans if needed in
.agent/operating-system/plans/
Core Workflow
- Understand the request, constraints, and risk tier
- Check
.agent/operating-system/product/README.mdfor repo intent - Create or update a plan in
.agent/operating-system/plans/for material work - Request approval before any approval-boundary action
- Implement in small, verifiable increments
- Keep decisions and documentation synchronized with implementation
- Store durable evidence when work benefits from traceability
Mandatory Artifacts
- ADRs live in
.agent/operating-system/decisions/ - Plans live in
.agent/operating-system/plans/active,backlog, orhistorical - Durable repo-wide standards live under
.agent/policies/ - Tool-specific decisions go in
packages/<tool>/decisions/(optional)
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 · 73 lines · 686 tokens per session scan A e53e485c1003
sign-tools AGENTS.md is an instructions file published in the GitHub repository sign-protocol/sign-tools (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 686 tokens to every session, about $0.0034 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 2026-08-31.
Other instructions, from other repositories
m_flow AGENTS.md
AGENTS.md instructions for FlowElement-xinliuyuansu/m_flow, covering m-flow — developer & agent reference, 1. repository map, extension points, 2. local development and python backend (requires python 3.10 – 3.13).
open-ontologies CLAUDE.md
Instructions for fabio-rovai/open-ontologies, covering open ontologies, ontology engineering workflow, generate, validate and load and reason.
engraphis CLAUDE.md
Instructions for Coding-Dev-Tools/engraphis, covering claude.md, the one rule that prevents most mistakes, before you say "done" — run the canonical gate, slash commands available here and working style in this repo.
kglite CLAUDE.md
Instructions for kkollsga/kglite, covering kglite — claude code conventions, build & test, architecture, the boundary principle (wrappers vs core) — summary and in-memory is the core product.
tpu_performance_autoresearch_wiki GEMINI.md
Instructions for vlasenkoalexey/tpu_performance_autoresearch_wiki, covering gemini/antigravity operating rules, platform adaptation (claude code → gemini/antigravity), 1. skills — native, no emulation, 2. never-stop hook & retrospectives and 3. session and transcript resolution.
tpu_performance_autoresearch_wiki AGENTS.md
Instructions for vlasenkoalexey/tpu_performance_autoresearch_wiki, covering codex instructions, compatibility, operating rules and codex translation notes.