A command that compiles a FIBER decision context from a world file and a query, then reports the oracle result, omitted data, and certificate hash. A certificate hash is a compact value used to check that the result has not changed.

Use it to compile contexts, inspect oracle status and evidence, review omission accounting, and obtain a certificate digest.

It gives a recorded decision result with details about omissions and a way to identify the exact compiled context.

compile — Command for coding agents by AURORA-NEURO: A command that compiles a FIBER decision context from…

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 commands/aurora-neuro/aurora-agent/compile

Clone the repo

git clone --depth 1 https://github.com/AURORA-NEURO/aurora-agent

Or install aurora-agent, the plugin that ships this one along with the rest of its 4 skills, 7 commands, 1 agent.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/aurora-neuro/aurora-agent/compile.svg)](https://agentmods.dev/commands/aurora-neuro/aurora-agent/compile)

Your own site

<a href="https://agentmods.dev/commands/aurora-neuro/aurora-agent/compile"><img src="https://agentmods.dev/badge/commands/aurora-neuro/aurora-agent/compile.svg" alt="Measured on agentmods" height="20"></a>

Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 439 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.

Model	Per session	Once invoked
Fable 5	$0.00025	$0.00439
Opus 5	$0.00013	$0.00219
Sonnet 5	$0.00005	$0.00088
Haiku 4.5	$0.00003	$0.00044

Measured 4d ago against content hash 12a9d605d572, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compile 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.

plugins/aurora-agent/commands/compile.md · 29 lines

What it actually says

Compile a decision context with the aurora-agent FIBER compiler and report the result faithfully.

Resolve the aurora-agent checkout: $AURORA_AGENT_ROOT if set, else ~/aurora-agent, else ~/bioprism. The CLI is <root>/target/release/bioprism (.exe on Windows). If missing, tell the user to build it: cargo build --release --offline -p bioprism-cli.
Parse arguments: $ARGUMENTS may name a world and query path (relative to the root). Defaults: world fixtures/fiber-v0.1/radiogenomic_world.json, query fixtures/fiber-v0.1/leakage_query.json.
Run from the checkout root: bioprism --json context compile --world <world> --query <query>
Interpret the exit code with the retryability matrix: 0 ok · 1 assertion_failed (a verdict, not an error) · 2 usage/terminal · 3 invalid_input/terminal · 4 compile_failed/retry-after-change · 5 io/retry-as-is · 6 conflict/terminal · 7 policy_denied/retry-after-change · 8 indeterminate/retry-after-change · 9 stale/retry-as-is. In --json mode the same decision is error.retryability.
Report, verbatim from the JSON envelope: the oracle status and witnesses (an invalid status is a finding about the data — integrity violations — not a tool failure), selected vs omitted fact counts, supports_sufficiency_claim, protected_closure_satisfied, and the certificate_sha256. Never summarize omissions away.

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.

4d ago First seen · 29 lines · 25 tokens per session scan A 12a9d605d572

Subscribe to this mod's changes

compile is a command published in the GitHub repository AURORA-NEURO/aurora-agent (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 25 tokens to every session and 439 once invoked, about $0.0001 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 2026-08-31.

claude claude-plugin decision-support mcp mcp-server model-context-protocol

compile

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

OPSX: Propose

10-optimization-finalization

checklist

clarify

specify

converge