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/universalgit 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 | $0.08704 | $0.08704 |
| Opus 5 | $0.04352 | $0.04352 |
| Sonnet 5 | $0.01741 | $0.01741 |
| Haiku 4.5 | $0.00870 | $0.00870 |
Grade A, and why
contexture universal.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 — 377 lines — stays where its author put it; the contents beside it link to each section on GitHub.
universal rules
Auto-loaded by Copilot when editing files matching
**. Generated fromarchitectural-rules/universal/— do not hand-edit.
Autonomy default
The default autonomy posture for this project is balanced effort / stop-at-criteria-met / ask-only-on-forks (the typed values live in this file's autonomy: frontmatter). It is the lowest tier of the autonomy contract's precedence (live > kickoff > inferred > default > implicit-default): a per-task /autonomize kickoff or a live steer overrides it; absent both, this is what the workflow organs read. See autonomize.
Override this default per project by placing an autonomy-default.md in the user or project overlay tier (~/.claude/architectural-rules/universal/ or <repo>/.claude/rules/universal/) with a different autonomy: block — the standard overlay cascade (project > user > shipped) applies, no parallel config engine. /autonomize's save-as-default flow writes the project-tier file for you.
/autonomize and the organs read the typed autonomy: frontmatter values from the resolved file directly — not via the rule-body resolver (resolve-rules.js), which emits prose bodies for priming and does not carry custom frontmatter keys. This file is a rule (it lives in the overlay tree for cascade + override + disable) whose payload is its frontmatter, not its body. relevance: on-demand keeps it off the always-on floor — the values are read when the contract resolves, never paid every turn.
Canonical tool commands
Pin the command next to the verb, not just the verb. The verb is the
policy ("read PR comments"); the command is the implementation. Re-deriving the
flags every session is a tax that pays nothing — the answer is the same each
time, and a wrong improvisation (missing --paginate, truncated output) is a
silent failure the agent won't notice.
Resolution order: a project's CLAUDE.md ## Canonical commands section (or
<repo>/.claude/canonical-commands.md) wins; these universal pins fill in; if no
pin exists, improvise as usual — no degradation.
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 · 377 lines · 8,704 tokens per session scan A 7eda5ee66a5e
contexture universal.instructions.md is an instructions file published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 8,704 tokens to every session, about $0.0435 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.