dossier-pass-b-falsification

dossier-pass-b-falsification is an agent for Claude Code from synaptiai/synapti-marketplace. It costs 80 tokens per session (1,401 once invoked), scanned A, original, Apache-2.0.

An independent review agent that tries to disprove a documentation package by tracing real system paths from source files through code, data storage, deployment, and monitoring.

In plain words
What is it for?
Use it to test architecture and operational documentation against implementation details and end-to-end system behavior.
Why use it?
It finds places where the written project model does not match how the system actually works.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the dossier plugin — 10 skills, 9 commands, 6 agents, 2 hooks shipped together

Good fit Use it to test architecture and operational documentation against implementation details and end-to-end system behavior.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/synaptiai/synapti-marketplace/dossier-pass-b-falsification
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.

Clone the repo
git clone --depth 1 https://github.com/synaptiai/synapti-marketplace

Made for: Claude Code.

Or install dossier, the plugin that ships this one along with the rest of its 10 skills, 9 commands, 6 agents, 2 hooks.

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 dossier-pass-b-falsification

README.md
[![agentmods](https://agentmods.dev/badge/agents/synaptiai/synapti-marketplace/dossier-pass-b-falsification/github.svg)](https://agentmods.dev/agents/synaptiai/synapti-marketplace/dossier-pass-b-falsification)
Your own site
<a href="https://agentmods.dev/agents/synaptiai/synapti-marketplace/dossier-pass-b-falsification"><img src="https://agentmods.dev/badge/agents/synaptiai/synapti-marketplace/dossier-pass-b-falsification/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dossier-pass-b-falsification

Your own site · 80×15
<a href="https://agentmods.dev/agents/synaptiai/synapti-marketplace/dossier-pass-b-falsification"><img src="https://agentmods.dev/badge/agents/synaptiai/synapti-marketplace/dossier-pass-b-falsification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 80 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,401 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 $0.00080 $0.01401
Opus 5 $0.00040 $0.00700
Sonnet 5 $0.00016 $0.00280
Haiku 4.5 $0.00008 $0.00140

Measured 9d ago against content hash ddf9e1efb623, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

dossier-pass-b-falsification 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 9d 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.

plugins/dossier/agents/dossier-pass-b-falsification.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Verification Pass B — Model Falsification

You are a principal engineer, production operator, security architect, privacy engineer, and hostile-but-fair acquirer, reading a documentation package you did not write.

Your lens is falsification: trace the system from its sources and find where the package and reality diverge.

Independence Protocol

You MUST NOT have access to, or reason about:

  • The drafting transcript or any authoring rationale
  • The architecture documents treated as authority — they are the thing under test
  • Findings from pass A or pass C, in this round or any prior round
  • The reconciliation logic, corroboration counts, or how findings are merged
  • The author's self-score or any prior gate verdict

You ONLY receive: the package root · the resolved scope · the source roots · this lens · the round number.

If you catch yourself reasoning about what the other passes probably found, stop. Redundant findings cost nothing. Assumed-covered defects cost everything.

The stance

You are not checking whether the package is well-written. You are trying to break it.

Start from the sources. Read the architecture document only to know what claim you are testing — never as the authority for what the system does. A trace that begins in the architecture document and confirms the architecture document has tested nothing.

Do not treat the package as correct because it is polished or internally consistent. Confidence in prose is not evidence.

Step 1 — Select traces

Use the traces recorded in the project model so your findings are comparable to the package's own claims. Then look for what those traces omit — the omission is often the finding.

Execute at least verification.traceCount traces (default 10), covering:

  1. A primary product or user journey
  2. An identity, authorization, or trust decision
  3. Sensitive data from collection through deletion
  4. A code or product change through test, release, deployment, and rollback
  5. An external integration through both normal and error paths
  6. A dependency outage or partial failure
  7. A capacity, rate, latency, or cost boundary
  8. A backup, restore, or disaster scenario
  9. An alert and incident from detection through recovery
  10. An AI, model, or agent failure or abuse path, where applicable

Read the full file on GitHub · 113 lines

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. 9d ago First seen · 113 lines · 80 tokens per session scan A ddf9e1efb623

Subscribe to this mod's changes

dossier-pass-b-falsification is an agent published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 80 tokens to every session and 1,401 once invoked, about $0.0004 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 2026-09-03.

Related

Other agents, from other repositories

codebase-analyzer

Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :).

CaptainMe-AI/lead-dev-os · 44 tokens

codebase-locator

Locates files, directories, and components relevant to a feature or task. Call codebase-locator with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.

CaptainMe-AI/lead-dev-os · 68 tokens

agentmaster-retro

Transcript-driven analyze-fix-verify loop for the agentmaster skill suite itself. Use after a pipeline run leaves artifacts behind — .transcripts/ snapshots, root-level run transcripts, generated docs, or accumulated telemetry — when the user wants the suite's own skills to keep improving from real usage. Grades…

rhawk117/agentmaster · 121 tokens

code-analyst

Mid-cost interpretation — trace how code works across files, reproduce and analyze test failures, research dependency changelogs and upgrade impact, run code-graph and architecture queries. Use when the answer requires reading between files, interpreting command output, or external research. Also the escalation target…

rhawk117/agentmaster · 65 tokens

rot-antivenom

The Anti-Venom lens — Immunological Pattern Recognition, the Clinical Purifier. Perceives errors, bugs, logical threats and structural weaknesses as pathogens and neutralises them with surgical precision. Summon for verification, debugging, security review, error diagnosis, integrity audit, or any claim that needs…

Nova-Violet-Role/RoT-MoE · 79 tokens

debugger

Adversarial post-implement sweep agent. Given a plan path, changed-file list, sweep number, and lens, audits the implementation for bugs from that lens's perspective. Flag-only — never modifies code. Scope bounded to changed files + 2-hop dependencies. One finding per real issue; no style/naming/formatting feedback.

keez97/phase-gate · 71 tokens