ChainWeaver copilot-instructions.md

Project instructions for ChainWeaver, a codebase that uses path-specific guidance files to direct coding agents. They explain how to apply the nearest rules, preserve important invariants, update documentation with behavior changes, and use approved validation commands.

In plain words
What is it for?
Use them when changing ChainWeaver code or agent-facing documentation, especially across multiple subsystems, when checking invariants, or when running the project's required validation commands.
Why use it?
They prevent agents from guessing conventions or overlooking rules for a subsystem touched by a change. They also keep code, workflows, and their supporting documentation aligned.

Instructions file for GitHub Copilot

Install

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.

agentmods
npx agentmods add instructions/dgenio/chainweaver/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/dgenio/ChainWeaver

Made for: GitHub Copilot.

Per session 653 This file is loaded in full into every session.
When invoked 653 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00653 $0.00653
Opus 5 $0.00327 $0.00327
Sonnet 5 $0.00131 $0.00131
Haiku 4.5 $0.00065 $0.00065

Measured 2d ago against content hash 5e6243780c9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ChainWeaver 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 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.

.github/copilot-instructions.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions — ChainWeaver

Thin review-oriented layer. Canonical source of truth: AGENTS.md, the path-scoped AGENTS.md files it indexes, and docs/agent-context/.


Scoped guidance

Path-scoped AGENTS.md files carry durable subsystem rules (nearest file applies; the root file always applies and cannot be weakened). The canonical index is AGENTS.md § 11 — for a change spanning several subsystems, apply every scoped file whose subtree is touched. The detailed module inventory is module-map.md.

Review-critical rules

  • Review code and agent-facing docs together. If a PR changes behavior, invariants, architecture, or workflows, the corresponding docs must be updated in the same PR.
  • Invariants take priority over cleanup, simplification, or local refactors. See AGENTS.md § Core invariants.
  • Do not invent conventions. All coding style, naming, workflow, and testing rules are grounded in AGENTS.md and docs/agent-context/. If guidance is missing, surface the gap — do not guess.
  • Use authoritative commands exactly as written in AGENTS.md § Validation commands. Do not substitute alternative flags, paths, or invocations.
  • If you find a contradiction or stale content in any doc, flag it explicitly. Do not silently work around it.

Executor guardrails

executor.py has three hard invariants — no LLM calls, no network I/O, no randomness. These are non-negotiable. See invariants.md.

Vocabulary

Use Never use
flow chain, pipeline
tool function, action (when referring to a Tool instance)

Where to find guidance

Topic Canonical file
Architecture, boundaries, design traps architecture.md
Commands, CI, code style, testing, PR rules workflows.md
Hard rules, forbidden patterns invariants.md
Recurring mistake patterns lessons-learned.md
Definition-of-done, review gates review-checklist.md
Local pre-commit hook install + policy CONTRIBUTING.md § Pre-commit hooks

Read the full file on GitHub · 58 lines

Changes

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.

  1. 2d ago First seen · 58 lines · 653 tokens per session scan A 5e6243780c9e

Subscribe to this mod's changes

ChainWeaver copilot-instructions.md is an instructions file published in the GitHub repository dgenio/ChainWeaver (6 stars, last pushed 3d ago), licensed Apache-2.0. It adds 653 tokens to every session, about $0.0033 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.