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 commands/ackeskin/contexture/pr-triagegit 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/pr-triage)<a href="https://agentmods.dev/commands/ackeskin/contexture/pr-triage"><img src="https://agentmods.dev/badge/commands/ackeskin/contexture/pr-triage.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 | $0.00058 | $0.00258 |
| Opus 5 | $0.00029 | $0.00129 |
| Sonnet 5 | $0.00012 | $0.00052 |
| Haiku 4.5 | $0.00006 | $0.00026 |
Grade A, and why
pr-triage 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 3d 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 pr-triage skill for the current PR.
It fetches the unresolved review comments (read-only), groups them into an editable checklist (one row per comment, none silently dropped), and walks each one with you. Per comment you pick one outcome: Act — pr-triage classifies the code change as isolated (→ /dispatch) or cross-cutting (→ /orchestrate), confirms, and routes it; Skip/defer — the row stays on the checklist unhandled, you answer on GitHub yourself; Note — it captures your decision against the row so you have it when you write the reply.
It never drafts or posts replies and makes no GitHub call beyond the read-only comment fetch. You write every response yourself.
Manual trigger only — the skill does not auto-fire. See ~/.claude/skills/pr-triage/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.
- 3d ago First seen · 12 lines · 58 tokens per session scan A 01165d31c01b
pr-triage is a command published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 258 once invoked, about $0.0003 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 commands, from other repositories
bmad-init
This command initializes or updates BMad-Method (V6) in your project.
feat
Command "feat" from miounet11/ccjk, covering core workflow, 1. input analysis and type determination, 2. classification processing mechanism, 3. key execution principles and quality assurance points.
init-project
Initialize project AI context, generate/update root-level and module-level CLAUDE.md indexes.
CLAUDE
Last Updated: Mon Oct 27 19:39:26 CST 2025.
context
Analyze and optimize context configuration. Reviews CLAUDE.md, knowledge-core.md, and active context for optimization opportunities. Helps prevent context rot (39% improvement, 84% token reduction).
workflow
Complete Research → Plan → Implement workflow in one command. Invokes chief-architect to orchestrate all phases with quality gates and self-correction.