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 skills add nWave-ai/nWave --skill nw-cross-cutting-context-residencygit clone --depth 1 https://github.com/nWave-ai/nWaveWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nwave-ai/nwave/nw-cross-cutting-context-residency)<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-cross-cutting-context-residency"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-cross-cutting-context-residency/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-cross-cutting-context-residency"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-cross-cutting-context-residency.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.00743 |
| Opus 5.5 | $0.00011 | $0.00297 |
| Sonnet 5.5 | $0.00005 | $0.00149 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
nw-cross-cutting-context-residency 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 4d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Residency
Composition: Load with nw-cross-cutting-invariants; no forced sequence; return to its routing table for other concerns.
context:pay-on-demand-not-every-session — resident context is paid every session (STANDING)
Whoever needs it loads it; whoever does not need it must not pay for it in every session. Context injected at session start is a per-session tax on every reader, including the readers who will never touch that subject. Detail belongs where it is needed, at the moment it is needed — not resident.
Three residency classes; classify before you inject anything:
- MUST-BE-RESIDENT — if it is absent from context, it does not happen. The load-bearing case is a trigger: an instruction to arm, to check, to refuse. Nobody goes looking for what they do not know exists, so a trigger cannot be made reachable-on-demand — its absence is silent. Same for a safety warning whose omission causes harm before anyone would think to consult it.
- MAP-ONLY — the reader must know THAT a thing exists and roughly WHEN to reach for it. Not how it works. A name plus a one-line "reach for this when…" is the whole resident cost.
- REFERENCEABLE — pure detail, needed only by whoever is doing that specific thing.
Density is a second axis, independent of residency. Normative content cannot be GENERATED from code, but it can be COMPRESSED: doctrine is usually rules — subject · condition · action — written as narrative. A table says the same thing in a fraction of the bytes and reads better. Do not confuse "not derivable" with "not compressible"; measuring the first tells you nothing about the second.
The failure this clause prevents: a projection that ADDS instead of REPLACING. Retiring a duplicate is a saving; generating a new view beside a surviving hand-written one is a new divergence surface AND a bigger payload.
context:resident-doctrine-can-be-compensation-debt — resident prose that patches bad guidance is debt (STANDING)
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.
- 4d ago First seen · 56 lines · 27 tokens per session scan A 79b09258d987
nw-cross-cutting-context-residency is a skill published in the GitHub repository nWave-ai/nWave (631 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 743 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-03.
nw-cross-cutting-context-residency compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nw-cross-cutting-context-residencynWave-ai/nWave | Skill | 631 | yesterday | MIT | A | 27 | Claude Code |
| computer-usekirodotdev/KiroCrew | Skill | 4.8k | yesterday | Apache-2.0 | A | 62 | Claude Code, Codex |
| croncrystal-autobot/autobot | Skill | 47 | 5d ago | MIT | A | 10 | Claude Code, Codex |
| addpilotspace/ADD | Skill | 19 | 4d ago | MIT | A | 188 | Claude Code |
| agnostic-ai-gh-issueChemaclass/agnostic-ai | Skill | 27 | today | MIT | A | 28 | Claude Code |
| startcycle-graph-userhybridlabor-api/bdb-dev-optimized-agent-skills | Skill | 6 | 5d ago | Apache-2.0 | A | 102 | Claude Code, Codex |
| tddt1/tdder | Skill | 14 | yesterday | Apache-2.0 | A | 102 | Claude Code |