Stats
Actions
Tags
From Pact
Stress-tests ideas, plans, architecture frames, definitions, criteria, drafts, or done claims using Pact's packaged Jeremy Simulacrum. Use proactively before committing to categorical claims or when the user asks for Sim, Simulacrum, Jeremy-style pushback, or the strongest counterargument.
How this skill is triggered — by the user, by Claude, or both
Slash command
/pact:simulacrumThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use Pact's packaged Simulacrum rather than searching for a user-specific skill
Use Pact's packaged Simulacrum rather than searching for a user-specific skill or executable.
For a direct claim review:
pact review "$TARGET_REPO" --sim-only --claim "$CLAIM"
For multi-tool post-implementation review:
pact review "$TARGET_REPO" --claim "$DONE_CLAIM"
Read the persisted simulacrum.md. A successful process means Sim completed;
it does not mean Sim approved the claim. Adjudicate the critique, correct the
frame or work when warranted, and rerun the review.
Pact ships the Sim runtime and annotated corpus. Provider calls use the local
operator's ANTHROPIC_API_KEY or PACT_REVIEW_ANTHROPIC_API_KEY directly;
Pact does not proxy or subsidize them. The optional PACT_SIMULACRUM_CMD
variable is an explicit operator override only. Operators can override the
packaged Anthropic model IDs with SIMULACRUM_CLASSIFIER_MODEL and
SIMULACRUM_SPECIALIST_MODEL.
npx claudepluginhub jmcentire/pactCross-examines non-trivial decisions with a fresh-context adversary. Use before committing high-stakes code, architecture, or irreversible operations when correctness outweighs speed.
Scrutinizes ideas or plans adversarially: spawns skeptics across lenses like technical, economic, operational; advocate defends; synthesizes feedback report. No code or artifacts.
Probes docs, skills, plans, or claims for weaknesses, gaps, or unstated assumptions before shipping. Returns structured verdicts.