auditor
01Agent
You are a lightweight security auditor. When asked to review code, scan for.
1.0k 4d ago A 3 tokens
original MIT
1.0kStars on the repository
27Mods indexed here, across every type
4d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Agent
Loads alpha+beta, selects only alpha via ext:. Flip mutes beta.
1.0k 4d ago B 16 tokens
original MIT
Agent
Selects beta via ext:; the loaded alpha extension is muted.
1.0k 4d ago B 14 tokens
original MIT
Agent
Selects alpha but denylists alphawrite via disallowedtools.
1.0k 4d ago B 14 tokens
original MIT
Agent
An ext: selector cannot resurrect an excluded extension.
1.0k 4d ago B 10 tokens
original MIT
exclude-beta
06Agent
Loads alpha+beta, excludes beta via excludeextensions.
1.0k 4d ago B 11 tokens
original MIT
Agent
extensions:false — no extension tools at all.
1.0k 4d ago B 9 tokens
original MIT
fmt-array
08Agent
tools value format: YAML flow array.
1.0k 4d ago A 8 tokens
original MIT
Agent
tools value format: quoted CSV string.
1.0k 4d ago A 8 tokens
original MIT
Agent
tools value format: unquoted CSV.
1.0k 4d ago A 8 tokens
original MIT
Agent
isolated:true forces built-ins only, overriding extensions and ext:.
1.0k 4d ago B 13 tokens
original MIT
Agent
ext: selecting the lazy extension surfaces its sessionstart tool.
1.0k 4d ago B 12 tokens
original MIT
Agent
A lazy extension left out of the ext: flip stays muted.
1.0k 4d ago B 13 tokens
original MIT
Agent
A tool registered at sessionstart reaches the subagent (#125).
1.0k 4d ago B 13 tokens
original MIT
Agent
README: "The disallowedtools field is respected when determining write capability — an agent with tools: write + disallowedtools: write correctly gets read-only memory.".
1.0k 4d ago A 17 tokens
original MIT
Agent
A read-only memory agent. Per the README, agents without write/edit tools auto-get a read-only memory fallback: existing memory is injected, no write access is granted, and no memory directory is created (so project scope is safe here — nothing is written into the repo).
1.0k 4d ago A 16 tokens
original MIT
Agent
A write-capable memory agent. Per the README, agents with write/edit tools get full read-write memory; the memory tool set is completed (edit is auto-added) and a writable memory block is injected into the system prompt. Scope user so the memory dir is created under the hermetic HOME, never in the repo.
1.0k 4d ago A 15 tokens
original MIT
minimal
18Agent
Minimal agent — only description and body; every other field omitted.
1.0k 4d ago A 13 tokens
original MIT
Agent
Narrows alpha to a single tool via ext:ext-alpha.mjs/alpharead.
1.0k 4d ago B 18 tokens
original MIT
Agent
No ext: selector, so all loaded extensions' tools surface.
1.0k 4d ago B 13 tokens
original MIT
Agent
APPENDBODYMARKER — in append mode the parent prompt flows in verbatim, so the real session's system prompt contains BOTH the parent marker and this body.
1.0k 4d ago A 11 tokens
original MIT
Agent
REPLACEBODYMARKER — in replace mode the parent prompt is NOT inherited, so the real session's system prompt contains this body but not the parent's marker.
1.0k 4d ago A 14 tokens
original MIT
Agent
A skill-preloading agent. The skills: probe-skill entry must inject test/fixtures/.pi/skills/probe-skill.md into the real session's system prompt.
1.0k 4d ago A 12 tokens
original MIT
tools-narrow
24Agent
tools narrowed to two built-ins; extensions omitted (=> true).
1.0k 4d ago A 13 tokens
original MIT