contextweaver routing.instructions.md

Development instructions for ContextWeaver's routing engine. The engine organizes available choices and tools into graphs and trees, then routes requests while enforcing rules such as valid roots, reachable items, and no cycles.

In plain words
What is it for?
Use them before changing the routing code, including graph validation, grouping, tree building, route search, or tool catalog handling.
Why use it?
Routing changes can create invalid graphs or inconsistent serialized data. These rules help prevent broken paths, cycles, and unreachable tools from entering the system.

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/contextweaver/routing
Clone the repo
git clone --depth 1 https://github.com/dgenio/contextweaver

Made for: GitHub Copilot.

Per session 995 This file is loaded in full into every session.
When invoked 995 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 $0.00995 $0.00995
Opus 5 $0.00498 $0.00498
Sonnet 5 $0.00199 $0.00199
Haiku 4.5 $0.00100 $0.00100

Measured 2d ago against content hash ff8dc4fb4f92, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

contextweaver routing.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/instructions/routing.instructions.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Routing Engine — Agent Instructions

Path-scoped guidance for src/contextweaver/routing/. Read before modifying any file here.

ChoiceGraph validation invariants (graph.py)

ChoiceGraph._validate() enforces four rules — all must hold at all times:

  1. Root existsroot_id must be present in _nodes.
  2. Children resolve — every edge destination must exist in _nodes | _items.
  3. No cyclestopological_order() must succeed (raises GraphBuildError if not).
  4. All items reachable — every item in _items must be reachable from root_id.

Cycle detection is eager: add_edge() calls _creates_cycle() immediately and raises GraphBuildError before the edge is persisted. Do not bypass this check.

Serialisation via from_dict() rebuilds children / child_types from _edges to guarantee consistency — never rely on serialised node metadata for child lists.

TreeBuilder grouping strategies (tree.py)

TreeBuilder.build() tries three strategies in priority order:

  1. Namespace grouping — group by first dot-segment of item.namespace; requires ≥ 50 % of items to have a namespace and ≥ 2 groups.
  2. Jaccard clustering — farthest-first seeding over tokenize(_text_repr(item)); falls back if clustering yields < 2 groups.
  3. Alphabetical fallback — sort by item.name.lower(), split into even chunks.

The builder is deterministic: it sorts items by item.id before processing. Do not introduce randomness or non-deterministic ordering inside _build_subtree.

Every node has at most max_children children (default 20). Oversized groups are coalesced via _coalesce_groups() or re-split before adding edges.

Router beam-search constraints (router.py)

  • Deterministic tie-breaking: children are sorted (-score, id) — descending score, alphabetical ID for ties. Never change this sort key.
  • confidence_gap (default 0.15) widens the beam by 1 when rank-1 and rank-2 scores differ by less than the gap. Must stay in [0.0, 1.0].
  • Results are ranked (-score, item_id) — same determinism guarantee end-to-end.
  • The TF-IDF index is lazily built on first route() call via _ensure_index(). Items are indexed by sorted item_id before non-item (navigation) nodes; do not change order.
  • Fallback scoring (nodes not in TF-IDF index) uses jaccard() from contextweaver._utils — never duplicate this logic here.

Read the full file on GitHub · 88 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 · 88 lines · 995 tokens per session scan A ff8dc4fb4f92

Subscribe to this mod's changes

contextweaver routing.instructions.md is an instructions file published in the GitHub repository dgenio/contextweaver (9 stars, last pushed 3d ago), licensed Apache-2.0. It adds 995 tokens to every session, about $0.0050 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.

Related

Other instructions, from other repositories