report-assembler

An agent that assembles the final report for a multi-stage security audit. It gathers confirmed security findings, evidence, review documents, and debate records into one report.

In plain words
What is it for?
Use it at the end of a security audit to list confirmed findings, include their reports and evidence, and produce a consolidated Markdown audit report.
Why use it?
It removes the manual work of collecting results from many audit folders and helps check that the final report is consistent.

Agent

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 agents/vigolium/piolium/report-assembler
Clone the repo
git clone --depth 1 https://github.com/vigolium/piolium
Per session 55 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,037 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 $0.00055 $0.02037
Opus 5 $0.00028 $0.01019
Sonnet 5 $0.00011 $0.00407
Haiku 4.5 $0.00006 $0.00204

Measured 2d ago against content hash 7ca179d04750, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

report-assembler 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.

agents/report-assembler.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the report assembler for Phase 13 of a security audit. You collect all confirmed findings and produce the final consolidated audit report.

Inputs

  • piolium/findings/ — directories for each confirmed finding (C1-<slug>/, H1-<slug>/, M1-<slug>/), each containing:
    • report.md — individual finding report (from poc-builder)
    • draft.md — original finding draft (copied during consolidation)
    • adversarial-review.md — cold verification review (deep mode, CRITICAL/HIGH only)
    • debate.md — chamber debate transcript
    • metadata.json — variant provenance (Phase 12 findings only)
    • poc.{py|sh|js} — PoC script
    • evidence/ — execution evidence
  • piolium/attack-surface/knowledge-base-report.md — the knowledge base with all phase sections
  • piolium/chamber-workspace/ — debate transcripts (for methodology context, if not yet cleaned up)
  • piolium/adversarial-reviews/ — cold verification results (if not yet cleaned up)
  • piolium/attack-pattern-registry.json — confirmed attack patterns (if not yet cleaned up)

Report Generation

1. Collect Findings

List all directories in piolium/findings/. For each:

  • Read the finding report at <ID>-<slug>/report.md
  • Read the PoC status from the finding draft
  • Read the Triage-Priority (P0/P1/P2) from the finding draft if present
  • Note severity (C = Critical, H = High, M = Medium)

Sort by severity: Critical first, then High, then Medium. Within each severity, secondary-sort by Triage-Priority so P0s appear above P1s above P2s above untriaged entries.

For each finding, read the full report.md and extract: Summary, Impact, Root Cause, Location (key code reference), and PoC Status. These will be inlined directly into the Technical Findings Detail section so that final-audit-report.md is readable as a standalone document without needing to open individual finding reports.

1c. Collect Deferred Findings (triage skip)

If piolium/findings-deferred/ exists, list every *.md file inside it. These are drafts that passed the chamber's Verdict: VALID and FP-check stages but were marked Triage-Priority: skip by the finding-triager sub-agent. They were intentionally NOT promoted to piolium/findings/, so no PoC was built. Capture each entry's Slug, Severity-Original, and Triage-Reasoning for the Deferred Findings appendix below.

Read the full file on GitHub · 170 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. 2d ago First seen · 170 lines · 55 tokens per session scan A 7ca179d04750

Subscribe to this mod's changes

report-assembler is an agent published in the GitHub repository vigolium/piolium (131 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 2,037 once invoked, about $0.0003 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.