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/ackeskin/contexture/linuxgit clone --depth 1 https://github.com/AcKeskin/contextureWhat 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 | $0.01227 | $0.01227 |
| Opus 5 | $0.00613 | $0.00613 |
| Sonnet 5 | $0.00245 | $0.00245 |
| Haiku 4.5 | $0.00123 | $0.00123 |
Grade A, and why
contexture linux.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 yesterday.
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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
linux rules
Auto-loaded by Copilot when editing files matching
**. Generated fromarchitectural-rules/linux/— do not hand-edit.
ipc-and-signals
In a signal handler, call ONLY functions listed in the async-signal-safe set (man 7 signal-safety); malloc, printf, and most libc functions are NOT safe — they may hold internal locks that the signal interrupted, causing deadlock. (man 7 signal-safety, POSIX.1-2017 §2.4.3)
Handle signals in the main event loop, not inside handlers: write a byte to a self-pipe in the handler and poll/epoll the read end, or block the signal set with pthread_sigmask(SIG_BLOCK, ...) and create a signalfd(2) over that same mask to receive signals as readable events (without the block, the default disposition still fires and the fd never sees them); this keeps all logic outside the async-signal-safe constraint. (man 2 signalfd, man 7 signal-safety)
In multithreaded programs, use pthread_sigmask to block signals in worker threads and deliver them to exactly one designated thread (or via signalfd); signal delivery to an arbitrary thread is uncontrollable and races with thread-local state. (man 3 pthread_sigmask, POSIX.1-2017 §2.4.1)
With epoll in edge-triggered mode (EPOLLET), drain the fd completely (read/recv until EAGAIN/EWOULDBLOCK) on each event; a single partial read leaves data in the buffer and suppresses future notifications, causing silent stall. (man 7 epoll — "Edge-triggered and level-triggered")
Never busy-wait on a fd or condition; use epoll/poll/select or a condition variable; busy-waiting starves other threads, pins a CPU core, and masks the actual blocking event. (POSIX.1-2017 §2.8.5, man 7 epoll)
Prefer signalfd over sigaction in event-loop programs; signalfd integrates into a unified epoll watch set, removing the need for careful async-signal-safe bookkeeping entirely. (man 2 signalfd)
Why: Signal handlers execute in an interrupted execution context where most libc internals are unsafe to call. The self-pipe trick is the portable pattern; signalfd(2) is the Linux-specific equivalent for bridging asynchronous signal delivery into synchronous event-loop code. Multithreaded signal delivery has undefined target-thread semantics unless masked and routed explicitly. Source: Linux man-pages / POSIX.
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.
- yesterday First seen · 52 lines · 1,227 tokens per session scan A a6326c65c029
contexture linux.instructions.md is an instructions file published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,227 tokens to every session, about $0.0061 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
agentic-workflow CLAUDE.md
Instructions for gtrabanco/agentic-workflow, covering claude.md, repository layout, working rules, authoring a skill and hand off, don't compose across a model/effort boundary.
ccjk AGENTS.md
Instructions for miounet11/ccjk, covering repository guidelines, source of truth, behavior, validation and notes.
ccjk CLAUDE.md
Instructions for miounet11/ccjk: 持久知识唯一来源:docs/CLAUDE-NOTES.md(请优先阅读本文档).
stenographer-mode copilot-instructions.md
Instructions for AkashAi7/stenographer-mode, covering steno mode — global instructions, contract, rules and levels.
context-engineering AGENTS.md
Instructions for fending/context-engineering, covering agents.md, what this project is, structure, standards and navigation.
capy CLAUDE.md
Claude Code instructions for serpro69/capy, covering claude.md, project, architecture, key packages and critical invariants.