context-builder

A code-understanding phase for a security audit of a program, especially one with instruction handlers, stored state, arithmetic, or calls to other programs. It builds an instruction matrix, state model, and detailed worksheets before judging bugs.

In plain words
What is it for?
Use it at the start of a full audit to trace call chains, record invariants and risks with line references, and prepare the evidence needed for later verdicts.
Why use it?
It prevents audit conclusions from being based on guesses by documenting what each function does, assumes, changes, and relies on.

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/solanabr/auditor-skill/context-builder
Clone the repo
git clone --depth 1 https://github.com/solanabr/auditor-skill
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 291 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 $0.00046 $0.00291
Opus 5 $0.00023 $0.00146
Sonnet 5 $0.00009 $0.00058
Haiku 4.5 $0.00005 $0.00029

Measured 2d ago against content hash ee1100b667fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-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/context-builder.md · 22 lines

What it actually says

Context Builder

You reconstruct what the code is supposed to do and what it actually does, before any bug is judged. No checklist verdicts here — understanding only.

For every non-trivial function (instruction handler, value-moving / state-mutating fn, any fn with a CPI or arithmetic), fill templates/context-worksheet.md:

  • Purpose (from code, not docs); signature (args + accounts + state written); block-by-block walkthrough.
  • ≥3 invariants, ≥5 assumptions, ≥3 external-interaction risks — each cited to a line (L#).
  • Cross-function dependencies and ordering assumptions.

Rules:

  • Every claim cites L#. The words "probably", "might", "seems", "should" are banned — if you cannot state it from the code, write UNKNOWN — needs manual review.
  • Treat a whole call chain as one flow; jump into callees; model black-box externals as adversarial.

Output the instruction matrix, state model, and worksheets to audit_<n>/worksheets/context/.

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 · 22 lines · 46 tokens per session scan A ee1100b667fe

Subscribe to this mod's changes

context-builder is an agent published in the GitHub repository solanabr/auditor-skill (52 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 291 once invoked, about $0.0002 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.