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/routinggit 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 | $0.00995 | $0.00995 |
| Opus 5 | $0.00498 | $0.00498 |
| Sonnet 5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00100 | $0.00100 |
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.
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:
- Root exists —
root_idmust be present in_nodes. - Children resolve — every edge destination must exist in
_nodes | _items. - No cycles —
topological_order()must succeed (raisesGraphBuildErrorif not). - All items reachable — every item in
_itemsmust be reachable fromroot_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:
- Namespace grouping — group by first dot-segment of
item.namespace; requires ≥ 50 % of items to have a namespace and ≥ 2 groups. - Jaccard clustering — farthest-first seeding over
tokenize(_text_repr(item)); falls back if clustering yields < 2 groups. - 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 sorteditem_idbefore non-item (navigation) nodes; do not change order. - Fallback scoring (nodes not in TF-IDF index) uses
jaccard()fromcontextweaver._utils— never duplicate this logic here.
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 · 88 lines · 995 tokens per session scan A ff8dc4fb4f92
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.
Other instructions, from other repositories
mattpocock-skills-zh CLAUDE.md
Instructions for devcxl/mattpocock-skills-zh, a project described as: Matt Pocock 技能集的中文翻译版 — 地道中文,原汁原味的技术术语。基于 mattpocock/skills 复刻。每日中午12点钟同步.
open-skill-sunset AGENTS.md
Instructions for ooocooc/open-skill-sunset, a project described as: Local, read-only audit for stale AGENTS.md, CLAUDE.md, and generic SKILL.md instructions.
AgentLint CLAUDE.md
Instructions for 0xmariowu/AgentLint, covering agentlint, local test (run before push), session checklist, rules and workflow.
agent-context-os CLAUDE.md
Claude Code instructions for conorbronsdon/agent-context-os, covering who i am, slash commands (claude code), when to load additional context, thought-partner mode and safety contract.
agent-skills AGENTS.md
Instructions for simota/agent-skills, covering agents.md — claude-skills, repository purpose, language policy, repository structure and skill authoring conventions.
Library-First-Engineering copilot-instructions.md
Instructions for StChiotis/Library-First-Engineering: You are an AI agent operating in a Library-First Engineering (LFE) repository. This adapter is a pointer. Canonical rules live in human-readable docs.