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.
git clone --depth 1 https://github.com/AcKeskin/contextureWrote 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/commands/ackeskin/contexture/extract-conventions)<a href="https://agentmods.dev/commands/ackeskin/contexture/extract-conventions"><img src="https://agentmods.dev/badge/commands/ackeskin/contexture/extract-conventions/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/commands/ackeskin/contexture/extract-conventions"><img src="https://agentmods.dev/badge/commands/ackeskin/contexture/extract-conventions.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 | $0.00040 | $0.00292 |
| Opus 5.5 | $0.00016 | $0.00117 |
| Sonnet 5.5 | $0.00008 | $0.00058 |
| Haiku 4.5 | $0.00004 | $0.00029 |
Grade A, and why
extract-conventions 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 1mo 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
Run the extract-conventions skill for the current context.
/extract-conventions <scope> observes a scope (a directory, module, or language) and authors a project-tier conventions.md capturing its dominant, confidently-observed conventions. Examples:
/extract-conventions— prompts for a scope./extract-conventions src/auth/— extracts conventions from that subtree./extract-conventions csharp— extracts the C# conventions across the project.
The skill samples representative files, detects mechanical conventions deterministically (case style, prefixes, import ordering) and semantic conventions by model judgment (comment style, idioms — flagged lower-confidence), presents them grouped by category with evidence and confidence, and writes nothing until you accept/edit/reject per category. On accept it writes <project>/.claude/rules/<lang>/conventions.md (project rule tier), delegating the idiomatic prose to the scope's language-pro agent. A convention that contradicts a shipped universal rule is flagged at confirm time — never silently overridden.
Mode A only — never auto-fires. See ~/.claude/skills/extract-conventions/SKILL.md for the full procedure.
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.
- 1mo ago First seen · 16 lines · 40 tokens per session scan A 3e5c827368ba
extract-conventions is a command published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 292 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
assemble-team
Assemble a pre-built agent team for parallel work - review, feature, debug, cross-platform, full-stack, or research.
review-code
Trigger a comprehensive code review on recent changes or specified files.
review-feedback
Review a given code review markdown document, GitHub PR review, or inline feedback — corroborate each point against actual code, then implement valid changes.
address
Address code review feedback — corroborate, validate, and implement changes from a review's final.md.
sync-reviewers
Sync reviewer metadata from markdown files to reviewers-meta.json for the dashboard.
translate-review-to-single-human
Translate a multi-reviewer code review into a single human-voice GitHub PR comment.