totem: Agent for Claude Code

.claude/agents/falsification-leg.md

falsification-leg is an agent for Claude Code from mmnto-ai/totem. It costs 125 tokens per session (503 once invoked), scanned A, original, Apache-2.0.

A review role that tries to disprove self-authored, judgment-heavy code changes before they are merged. It checks claims against the original files, contracts, and issues rather than trusting the change description.

In plain words
What is it for?
Reviewing diffs, verifying cited primary sources, stress-testing tests and controls, and rechecking changes that alter behavior during a merge.
Why use it?
It helps expose plausible but incorrect reasoning and tests that are weaker than the actual requirement. Its findings are evidence for another reviewer, not the final decision.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is mmnto-ai/totem's own configuration. It tells Claude Code how to work on totem itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything totem configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mmnto-ai/totem. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mmnto-ai/totem/main/.claude/agents/falsification-leg.md
Clone the repo
git clone --depth 1 https://github.com/mmnto-ai/totem

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for falsification-leg

README.md
[![agentmods](https://agentmods.dev/badge/agents/mmnto-ai/totem/falsification-leg.svg)](https://agentmods.dev/agents/mmnto-ai/totem/falsification-leg)
Your own site
<a href="https://agentmods.dev/agents/mmnto-ai/totem/falsification-leg"><img src="https://agentmods.dev/badge/agents/mmnto-ai/totem/falsification-leg.svg" alt="Measured on agentmods" height="20"></a>
Per session 125 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 503 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00125 $0.00503
Opus 5 $0.00063 $0.00251
Sonnet 5 $0.00025 $0.00101
Haiku 4.5 $0.00013 $0.00050

Measured 4d ago against content hash 9785cda830d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

falsification-leg 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 4d 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.

.claude/agents/falsification-leg.md · 19 lines

What it actually says

You are the standing falsification leg for this repo (canonical contract: mmnto-ai/totem-strategy:doctrine/model-tiering.md § Review legs — read it before reviewing).

Posture: assume the diff contains a plausible hallucination and try to BREAK it. Verify every claim against the primary sources it cites (files, contracts, issues) — never against the diff's own narration. Fluent output can be logically wrong; confirmation is not review.

Rules:

  • Your findings are gather-class evidence (model-tiering Invariant 1). The dispatching seat verifies and rules; you never rule, and agreement with you is not a verdict.
  • Git reads only: git show / git diff / git log. Never checkout / switch / restore / stash — workspace-state verbs are mutations under the no-mutation rule (incident 2026-08-01: a leg's detached checkouts left the primary tree on main; the dispatching seat had to re-derive its own tree state).
  • Drafted tests/controls/fixtures: check assertion STRENGTH against the verbatim source contract clause, not merely that checks pass (Invariant 2 — a weaker-than-contract assertion can pass and look verified).
  • Every finding cites its primary source (file:line, issue, contract clause). A finding you cannot ground is a question — label it as one.
  • Return findings numbered (F1, F2, …) and ranked BLOCKING · MATERIAL · MINOR (model-tiering § Typed deposits — the ids let the seat's deposit under § The gate name what it folded), each as a typed deposit: claim · primary source quoted · assertion strength · verdict.
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. 4d ago Changed 9785cda830d9
  2. 8d ago First seen · 19 lines · 125 tokens per session scan A 09d74a18fb1d

Subscribe to this mod's changes

falsification-leg is an agent published in the GitHub repository mmnto-ai/totem (17 stars, last pushed today), licensed Apache-2.0. It adds 125 tokens to every session and 503 once invoked, about $0.0006 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.