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/dgenio/contextweaver/copilot-instructionsgit clone --depth 1 https://github.com/dgenio/contextweaverWhat 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 | $0.00835 | $0.00835 |
| Opus 5 | $0.00417 | $0.00417 |
| Sonnet 5 | $0.00167 | $0.00167 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
contextweaver 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
contextweaver — Copilot Instructions
AGENTS.mdis the single source of truth for shared rules, conventions, and module layout. This file contains review-critical rules that must be visible in GitHub and Copilot-specific guidance. Do not treat this file as a standalone reference.
Review-Critical Rules
- Review code and agent docs together. When a PR changes behavior that agent-facing docs describe (pipeline stages, public API, conventions, module layout), review the code change and the doc update as a unit. If the PR has no doc update, flag it.
- PRs that change any of these must trigger doc review:
workflows, invariants, architecture intent, review rules, path-specific conventions,
or the module map. Expect a corresponding update to
AGENTS.mdordocs/agent-context/. - Invariants take priority over cleanup, simplification, or local refactors.
Check
docs/agent-context/invariants.mdbefore proposing structural changes. - Do not invent conventions. All conventions must be grounded in
AGENTS.md,docs/agent-context/, or verifiable repository evidence. If you cannot find a rule, it does not exist — do not assume one. - Use authoritative commands. Run
make ci(notmake testalone) as the validation gate. SeeAGENTS.mdfor the full command reference. - Surface contradictions. If you find conflicting guidance between docs, or between docs and code, flag the contradiction explicitly. Do not silently pick one side.
Hard Rules (auto-reject)
These cause automatic rejection in review. No exceptions.
- No
print()in library code. Use hooks or logging.__main__.py(CLI) is exempt. - No business logic in
__init__.py. Only re-exports allowed.
Copilot-Specific Guidance
Understand system-level intent before making changes. contextweaver has deliberate architectural boundaries (async context vs sync routing, protocol-based stores, 8-stage pipeline, complementary serialization layers). Changes that are locally correct but violate these boundaries will be rejected. Before modifying code, check:
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 · 63 lines · 835 tokens per session scan A 2453cc36417c
contextweaver copilot-instructions.md is an instructions file published in the GitHub repository dgenio/contextweaver (9 stars, last pushed 2d ago), licensed Apache-2.0. It adds 835 tokens to every session, about $0.0042 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
kindex CLAUDE.md
Instructions for jmcentire/kindex, covering kindex — knowledge graph for ai-assisted workflows, running tests, all tests, specific module and with coverage.
ChainWeaver AGENTS.md
Instructions for dgenio/ChainWeaver, covering chainweaver — agent instructions, 1. project identity, 2. domain vocabulary, 3. repository layout and 4. core invariants.
ChainWeaver copilot-instructions.md
Instructions for dgenio/ChainWeaver, covering copilot instructions — chainweaver, scoped guidance, review-critical rules, executor guardrails and vocabulary.
ChainWeaver testing.instructions.md
Instructions for dgenio/ChainWeaver, covering testing instructions — chainweaver, framework, structure, fixtures and coverage patterns.
ChainWeaver python-source.instructions.md
Instructions for dgenio/ChainWeaver, covering python source instructions — chainweaver, module conventions, pydantic patterns, exception patterns and export rules.
ChainWeaver chainweaver.instructions.md
Instructions for dgenio/ChainWeaver: Also read the nearest path-scoped AGENTS.md for the subtree you are changing — the index is in AGENTS.md § 11.