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/copilot-instructionsgit 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 | $0.00549 | $0.00549 |
| Opus 5 | $0.00275 | $0.00275 |
| Sonnet 5 | $0.00110 | $0.00110 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
sign-tools copilot-instructions.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 3d 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
GitHub Copilot Instructions for Sign Tools
This is a monorepo for tools supporting the SIGN-LANG open-source project. As Copilot/Codex, adhere to these guidelines:
Repository Purpose
- Mission: Provide reference implementations for SIGN-LANG ecosystem
- Structure: Monorepo with
packages/<tool>/for each tool - First Tool: sign-ingest (document → SIGN converter)
- Shared Code:
shared/for cross-tool utilities
Engineering Posture
- Be truthful and explicit
- Create durable artifacts
- Prioritize maintainability
- Use clear boundaries and small steps
Development Workflow
- Review request, constraints, and risk level
- Consult
.agent/operating-system/product/README.mdfor repo intent - For tool-specific work, read
packages/<tool>/SPEC.mdfirst - For significant work, create/update plans in
.agent/operating-system/plans/ - Seek approval for high-risk actions
- Implement incrementally with verification
- Keep docs synchronized with code changes
Standards and Policies
- Follow
.agent/policies/agent-coding-standards.md - Review approval boundaries:
.agent/policies/approvals.md - Consider risk tiers:
.agent/policies/risk-tiers.md
Approval Requirements
Request human approval for:
- Irreversible data changes
- Security/auth modifications
- Production infrastructure changes
- New public integrations
- Security weakening changes
Documentation Updates
Documentation is part of the product. Update when system truth changes:
- Tool-specific changes:
packages/<tool>/docs - Shared changes:
shared/,docs/, repo README - Decisions:
.agent/operating-system/decisions/
Repository Structure
sign-tools/
├── .agent/ # Agentic OS (policies, plans, decisions)
├── packages/
│ └── sign-ingest/ # First tool
├── shared/ # Shared utilities
├── docs/ # Shared documentation
└── AGENTS.md, README.md, CONTRIBUTING.md
For Adding a New Tool
- Create
packages/<tool-name>/with README and SPEC.md - Follow existing tool patterns
- Update root README.md with tool description
- Create implementation plan if substantial
- Ensure code passes repo standards c:\CareerHighways\sign-tools.github\copilot-instructions.md
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.
- 3d ago First seen · 62 lines · 549 tokens per session scan A b08095ba6bea
sign-tools copilot-instructions.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 549 tokens to every session, about $0.0027 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.