fold

A command that creates a smaller version of a currently selected execution trace by collapsing repeated blocks of recorded instructions.

In plain words
What is it for?
Use it before searching or scanning a bound trace that contains repeated hash loops, encryption rounds, or virtual-machine dispatch blocks.
Why use it?
Large traces with repeated loops can be slow to search, so reducing repetition makes later analysis easier.

Command

Install

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.

agentmods
npx agentmods add commands/icloudza/algokiller-plugin/fold
Clone the repo
git clone --depth 1 https://github.com/icloudza/algokiller-plugin
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 323 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00037 $0.00323
Opus 5 $0.00018 $0.00161
Sonnet 5 $0.00007 $0.00065
Haiku 4.5 $0.00004 $0.00032

Measured 2d ago against content hash d98754f9b1f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fold 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 2d 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.

commands/fold.md · 15 lines

What it actually says

Use this when the bound trace is so large that subsequent trace_constscan / trace_search calls feel slow, especially when the trace contains long repeating instruction blocks (hash main loops, AES rounds in a loop, VM dispatch loops).

Steps:

  1. Sanity-check the binding. If no trace is bound, stop and tell the user.
  2. Run trace_fold with sensible defaults for the bound trace's shape. For hash-loop-heavy traces use block=4, threshold=100; for VM-dispatch heavy use block=2; for unknown use block=4, threshold=200. Direct the output to out_filename (relative, lands inside the current artifacts_dir).
  3. Report the size delta to the user: "trace_fold collapsed X MB → Y MB (Z %)". Pull the byte counts from the trace_fold response.
  4. Ask the user if they want to bind_trace to the folded version. If yes, call bind_trace(path=<folded path>, mode=<same mode>). The folded trace's line numbers do NOT correspond to the original, so any line-number anchors from prior analysis become invalid — warn the user before rebinding.

DO NOT silently rebind. The folded trace is a derivative artifact, and using it requires user acknowledgement that line numbers don't carry over.

Changes

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.

  1. 2d ago First seen · 15 lines · 37 tokens per session scan A d98754f9b1f1

Subscribe to this mod's changes

fold is a command published in the GitHub repository icloudza/algokiller-plugin (77 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 323 once invoked, about $0.0002 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 2026-08-30.