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 rules/b-fontaine/devoxx-2026/context-hygienegit clone --depth 1 https://github.com/b-fontaine/devoxx-2026Wrote 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/rules/b-fontaine/devoxx-2026/context-hygiene)<a href="https://agentmods.dev/rules/b-fontaine/devoxx-2026/context-hygiene"><img src="https://agentmods.dev/badge/rules/b-fontaine/devoxx-2026/context-hygiene.svg" alt="Measured on agentmods" 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 | $0.00246 | $0.00246 |
| Opus 5 | $0.00123 | $0.00123 |
| Sonnet 5 | $0.00049 | $0.00049 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade A, and why
context-hygiene 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.
What it actually says
Hygiène de contexte
Principes
- Une session = une tâche = une couche architecturale
- Ne lis que les fichiers nécessaires à la tâche en cours
- Préfère lire un fichier .feature ou un trait/interface plutôt que toute l'implémentation
- Quand tu ne sais pas où est quelque chose, utilise grep ciblé plutôt que de lire l'arborescence entière
Workflow recommandé
- Lis le fichier de spec/test concerné en premier
- Lis les interfaces/traits du domain
- Implémente dans une seule couche
- Vérifie (test + lint)
- Si la tâche suivante est dans une autre couche, propose un résumé des décisions avant de continuer
Signaux d'alerte
- Si tu as lu plus de 10 fichiers sans produire de code : tu explores trop
- Si tu répètes une correction déjà faite : le contexte est probablement saturé
- Si tu proposes un pattern différent de celui établi : relis le CLAUDE.md/AGENTS.md
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 · 26 lines · 246 tokens per session scan A 53b231f21849
context-hygiene is a cursor rule published in the GitHub repository b-fontaine/devoxx-2026 (5 stars, last pushed 4mo ago), licensed MIT. It adds 246 tokens to every session, about $0.0012 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 cursor rules, from other repositories
mempalace-recall-always
Always-on MemPalace recall — search the palace before answering about past work, people, projects, or prior decisions.
dreamd-recall
Recall lessons, decisions, and prior context from the .agent/ memory daemon. Use when starting work in a project that has a .agent/ folder, when the user references a past decision, or when you are about to make a choice that has a documented prior.
session-memory
Use at conversation wrap-up or when the user explicitly indicates end-of-session — capture residual lessons not captured in-flight.
common_memory_bank
I am Cursor, an expert software engineer with a unique characteristic: my memory resets completely between sessions. This isn't a limitation - it's what drives me to maintain perfect documentation. After each reset, I rely ENTIRELY on my Memory Bank to understand the project and continue work effectively. I MUST read…
context-recorder-system
Context Recorder System (记录员系统) - 模块化索引文件.
memsprout
Cursor rule "memsprout" from memsprout/agents, covering using memsprout, search first, capturing, spaces and topics and files.