AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Sf Prune

skill-daviddme-claude-skills-sf-prune · by daviddme

Find deployed StrategyFactory bots whose underlying strategy's edge is decaying, and optionally pause them. Use when the user asks "kill the dead bots / prune my portfolio / pause the losers / which of my bots are dying / clean up the bot roster". Writes state via PATCH only when --apply is passed.

↗ Repository
— No reviews yet
0 installs
6 views
0.0% view→install

Install

$ agentstack add skill-daviddme-claude-skills-sf-prune

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Sf Prune? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

sf-prune

Audit-and-clean for your deployed roster. For every ACTIVE bot, pulls the underlying strategy and runs the same edge-decay heuristic as [sf-edge-watch](../sf-edge-watch/SKILL.md). Bots whose strategies are decaying or dead are listed; with --apply they get paused via PATCH /bots/:id.

When to use

  • "Prune the bot roster"
  • "Pause anything that's dying"
  • "Show me which of my bots have lost their edge"

How to run

# Dry run — lists candidates, never PATCHes
python sf-prune/prune.py [--include soft|decaying|dead] [--json]

# Actually pause flagged bots
python sf-prune/prune.py --apply [--include soft|decaying|dead]

Defaults: --include decaying,dead (soft = watch but don't touch).

Output

Table sorted worst-first: bot name, strategy, status, flags. With --apply, also prints PATCH result per bot.

Safety

  • Without --apply, this is fully read-only.
  • --apply PATCHes one bot per call. The shared client respects the

server-side 10-second per-bot cooldown automatically.

  • Only ACTIVE bots are considered. PAUSED/DRAFT/DISABLED are skipped.
  • This skill does not delete bots — it only pauses them. To re-activate

later, use PATCH /bots/:id with action: "reactivate".

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills