From 98990bae45949a07974ba42405fed305fb654920 Mon Sep 17 00:00:00 2001 From: Ahmed Allam Date: Thu, 16 Jul 2026 11:38:28 +0000 Subject: [PATCH] docs(prompts,skills): scope cleanup to own files; dedupe JSONL by URL Address Greptile review: - system_prompt: only clean up your own task's files; don't delete another agent's files in the shared workspace unless confirmed unused. - katana.md: extract+dedupe URLs with jq before removing raw .jsonl (sort -u on JSONL compares whole records, not URLs). --- strix/agents/prompts/system_prompt.jinja | 2 +- strix/skills/tooling/katana.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/strix/agents/prompts/system_prompt.jinja b/strix/agents/prompts/system_prompt.jinja index 6141179b..2a7b065d 100644 --- a/strix/agents/prompts/system_prompt.jinja +++ b/strix/agents/prompts/system_prompt.jinja @@ -244,7 +244,7 @@ DISK & SCRATCH HYGIENE: - /workspace is a shared, finite disk used by all agents at once — be a considerate tenant - Prefer bounded recon: scope crawls and scans by depth, duration, and target rather than "collect everything" - Send large tool output to /workspace/scratch/, and once you've extracted what you need (e.g. a URL/endpoint list), remove the raw output -- If disk gets tight or a write fails for space, check what's large under /workspace and clean up before continuing +- If disk gets tight or a write fails for space, check what's large under /workspace and clean up files from your own task; leave another agent's files unless you've confirmed they're no longer in use MANDATORY INITIAL PHASES: diff --git a/strix/skills/tooling/katana.md b/strix/skills/tooling/katana.md index 1abb5da2..66b4928d 100644 --- a/strix/skills/tooling/katana.md +++ b/strix/skills/tooling/katana.md @@ -63,7 +63,7 @@ Keeping output manageable: - katana does not cap its own output size, so bound crawls with `-ct` (crawl-duration) and `-d` (depth); on large sites an unbounded `-jsl` / `-kf all` deep crawl can grow very large. - Reserve deep JS crawling (`-jsl`, `-kf all`, higher `-d`) for a specific narrowed target rather than broad scopes. - After a crawl, glance at output size (`du -sh `); if it looks outsized for the scope, tighten `-d`/`-ct`/`-ef` or split per host. -- Dedupe and reduce before use (`sort -u`), and remove the raw `.jsonl` once you've parsed the URLs you need. +- For JSONL output, extract and dedupe URLs before use (`jq -r '.url' | sort -u > urls.txt`), then remove the raw `.jsonl` once you've preserved any metadata you still need. Usage rules: - Keep `-d`, `-c`, `-p`, and `-rl` explicit for reproducible runs.