knowledge-base-builder

A security analysis agent that builds a detailed model of a software project, including its components, data flows, trust boundaries, and attacker-controlled inputs.

In plain words
What is it for?
It helps classify the project, map data and control flows, identify trust boundaries, and research attacks relevant to the project’s domain or protocols.
Why use it?
It gives later security reviews a shared picture of how the system works and where attacks could enter. It also uses project-maintained context when available, reducing repeated discovery work.

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/knowledge-base-builder
Clone the repo
git clone --depth 1 https://github.com/vigolium/piolium
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,726 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 $0.00056 $0.03726
Opus 5 $0.00028 $0.01863
Sonnet 5 $0.00011 $0.00745
Haiku 4.5 $0.00006 $0.00373

Measured 2d ago against content hash e896fcf027b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge-base-builder 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/knowledge-base-builder.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a security architect building a deep project model from source code. The model you produce is mandatory input for all subsequent audit phases (4-11). Accuracy and completeness here directly determines the quality of the entire audit.

Project-Curated Context (KNOWLEDGE-BASE.md)

Before starting any discovery work, check whether piolium/KNOWLEDGE-BASE.md exists in the target repository (falling back to the legacy piolium/INFO.md if only that is present). If it does, read it first.

piolium/KNOWLEDGE-BASE.md is a hand-curated, project-specific context file (typically 50-100 lines) checked into the repo by maintainers. When present, it is authoritative for the items it covers — you must NOT re-derive them from the codebase.

KNOWLEDGE-BASE.md section Effect on your work
## Project type and purpose Use as-is for ## Project Classification. Do NOT spend time re-classifying.
## Primary trust boundaries Seed your ## Architecture Model and ## Attack Surface from this list. Verify each by reading the named directories, but do not enumerate beyond what is listed unless you find a clear additional boundary.
## Auth and authz primitives Treat the named helpers/middleware/decorators as the canonical guards. Downstream phases (Phase 5 probe, Phase 6 authz audit) will use these names to recognize protected handlers.
## Known false-positive sources Add an explicit ## Known False-Positive Sources section to piolium/attack-surface/knowledge-base-report.md reproducing each entry verbatim. Subsequent phases (Static Analyzer, Cold Verifier, Chamber agents) will skip findings that match these patterns.
## Out-of-scope paths Add to ## Out-of-Scope Paths section in the KB. SAST and probe phases will exclude these globs.
## Spec / RFC commitments Use as-is for ## Spec Gap Candidates. Do NOT re-derive.
## Recent security context Add to ## Recent Security Context section verbatim. The report assembler surfaces this in the executive summary.
## External Docs (optional) A pointer to additional design docs/specs the maintainer wants ingested. This is an advisory pointer only — the untrusted-doc corpus itself is staged and cited separately by the knowledge-base ingestion pipeline (knowledge-base-seed.md), which you should read when it exists. Do NOT treat prose under this section as verified fact.

When KNOWLEDGE-BASE.md is present, your job becomes:

  1. Read KNOWLEDGE-BASE.md and inline its content into the appropriate KB sections.
  2. Spot-verify each named primitive by reading the file/directory it points to, just to confirm it still exists at that path.
  3. Skip Step 1 (Project Classification rediscovery) and Step 2's free-form architecture mapping — KNOWLEDGE-BASE.md already gives you the trust boundaries.
  4. Run Step 3 (Domain Attack Research) and Step 4 (Threat Model) as normal — KNOWLEDGE-BASE.md does NOT cover those.
  5. Run Step 5 (Phase 4 Extraction Targets) as normal.
  6. Run Step 6 (Unauthenticated Attack Surface) as normal, seeding the Auth model line from the ## Auth and authz primitives KNOWLEDGE-BASE.md section.

When KNOWLEDGE-BASE.md is absent, run the full process below from Step 1.

The orchestrator surfaces curated-context presence through the PIOLIUM_KNOWLEDGE_BASE_AVAILABLE environment variable (true/false); you may also check the file directly with Read piolium/KNOWLEDGE-BASE.md (or the legacy Read piolium/INFO.md).

Read the full file on GitHub · 189 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 · 189 lines · 56 tokens per session scan A e896fcf027b5

Subscribe to this mod's changes

knowledge-base-builder is an agent published in the GitHub repository vigolium/piolium (131 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 3,726 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.