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/rustgit 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 | $0.04178 | $0.04178 |
| Opus 5 | $0.02089 | $0.02089 |
| Sonnet 5 | $0.00836 | $0.00836 |
| Haiku 4.5 | $0.00418 | $0.00418 |
Grade A, and why
contexture rust.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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rust rules
Auto-loaded by Copilot when editing files matching
**/*.rs. Generated fromarchitectural-rules/rust/— do not hand-edit.
Rust dependability and debug
- Destructors never fail (C-DTOR-FAIL).
Drop::dropcannot return aResult; if it could panic during unwinding, you get a process abort. If cleanup can fail meaningfully (e.g. flushing a buffered writer, committing a transaction), expose an explicitclose(self) -> Result<(), Error>that consumes the value, and haveDropperform a best-effort fallback (log on failure, never panic). - Destructors that may block have an explicit non-blocking alternative (C-DTOR-BLOCK). If
Dropcan wait on I/O / a lock / a thread join, providefn shutdown(self) -> ...so async / time-sensitive callers can opt out of the implicit wait. Document the blocking behavior onDropitself. - All public types implement
Debug(C-DEBUG).#[derive(Debug)]by default; manual impl only when the derived form leaks secrets (passwords, tokens) or is too noisy. MissingDebugblocksdbg!, breaksassert_eq!failure messages, and fails generic bounds that require it. Debugrepresentation is never empty (C-DEBUG-NONEMPTY). The output must let a reader distinguish two non-equal values.MyType(literally just the name) is useless; use the derived formatMyType { field: value, ... }or a manual impl that surfaces identifying state.
Why: dependability and debuggability are paid for in the type definition, not at the bug site. A panicking destructor or a Debug impl that returns "" are not noticed until production, by which point the cost of fixing is enormous.
Rust documentation
- Crate-level docs (
//!inlib.rs) are thorough and include runnable examples (C-CRATE-DOC). The first paragraph is a one-sentence elevator pitch that ends up indocs.rssearch results. - Every public item has at least one rustdoc example (C-EXAMPLE). Examples compile and run as doctests by default — verify with
cargo test --doc. Noignore/no_runannotations except when justified (network calls, platform-specific code). - Prose hyperlinks to relevant items (C-LINK). Use intra-doc links:
[`Vec`],[`Self::method`],[`crate::module::Item`]. Do not write bareVecin prose — link it. Cargo.tomlincludes complete metadata (C-METADATA):description,license(SPDX expression like"MIT OR Apache-2.0"),repository,documentation,readme,keywords(≤5),categories(from the docs.rs list),rust-version(MSRV).- Maintain release notes /
CHANGELOG.mddocumenting every significant change (C-RELNOTES). Follow [Keep a Changelog] format. Note breaking changes prominently. - Rustdoc hides implementation noise (C-HIDDEN). Use
#[doc(hidden)]on items that are public for macro-expansion reasons but not part of the API. Use#[doc(no_inline)]to prevent re-exports from cluttering listings.
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 · 123 lines · 4,178 tokens per session scan A ff703a423d41
contexture rust.instructions.md is an instructions file published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 4,178 tokens to every session, about $0.0209 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.