Skill Claude CodeCodex
Add a new crate to the bioprism workspace implementing a blueprint section, including registering it, choosing dependencies without creating cycles, and the honesty conventions every crate must follow. Use when starting a new module, when asked to cover an uncovered blueprint section, or when setting up work for a…
Skill Claude CodeCodex
Verify the CPython reference, the eager Rust path and the indexed store still agree byte for byte on a Context Certificate digest. Use after touching canonical serialization, hashing, compiler passes, the store, or any serde configuration, and before any release or wire-format change.
Skill Claude CodeCodex
Decide which blueprint modules are code before writing any, using the five verdicts this workspace discovered, and cite ids without inflating the coverage figure. Use when opening a blueprint section, when a section looks badly uncovered, when deciding what a crate should claim, or before writing any NN.MM token into…
Skill Claude CodeCodex
Find and fix the defect this workspace keeps producing — an error or a missing measurement collapsed into a benign default, so a refusal becomes indistinguishable from an answer. Use when writing or reviewing anything that compares two outcomes or feeds a published number, when auditing a crate, and whenever you are…
Skill Claude CodeCodex
Measure how much of a blueprint section is repeated template, in a way that another agent can reproduce and that will not disagree with the figure already recorded. Use when reporting how repetitive a section is, when your figure does not match docs/COVERAGE.md, or when deciding how much distinguishing content a batch…
Skill Claude CodeCodex
Pair every source-scanning hygiene test with a proof that it detects a planted violation, that its walk actually opened files, and that it is no laxer than the tool it mirrors. Use when writing or reviewing any test that greps a crate's own text — citation audits, hardcoded-constant checks, imputation scans…
Skill Claude CodeCodex
Verify a bioprism crate is genuinely green — tests passing and clippy at zero warnings — and recognise the environment failures that masquerade as test failures. Use before claiming a crate is done, after landing an agent's work, when a test count looks wrong or lower than expected, or when cargo test reports a…
Plugin Claude Code
Plugin marketplace listing 9 plugins: aurora-agent, aurora-backend, aurora-context, aurora-missions, aurora-integrate.
MCP server Claude CodeCodexCursor
MCP server "aurora-agent" as configured in AURORA-NEURO/aurora-agent. Launched with ./target/release/bioprism-mcp --root ..
Instructions file CodexOpenCode
AGENTS.md instructions for AURORA-NEURO/aurora-agent, covering aurora agent, what we can never compromise on, 1. honest labelling is the product, 2. invariants belong in the type system, not in comments and 3. determinism, byte for byte.
Instructions file
Claude Code instructions for AURORA-NEURO/aurora-agent: See AGENTS.md. It is the single source of truth for how to work in this repository; this file exists only so Claude Code finds it by its conventional name.
Plugin Claude Code
The AURORA Agent in one plugin: the bioprism MCP server (264 tools) wired into every session, FIBER decision-context commands (compile / explain / compare / validate / verify), mission preflight, an ops-auditor subagent, and skills for setup, the FIBER workflow, missions, and SDK integration. Requires a built…
Agent
Audit the aurora-agent control plane's operational evidence — snapshots, capability gates, domain activity, and the recovery matrix. Delegate to this agent when asked whether the aurora backend is healthy, what the gates say, what would survive a restart, or to summarize operational posture. It reports evidence…
Command
Compare the FIBER compiler against equal-engineering baselines (graph walks, lexical retrieval) and report which preserve the reference verdict.
Command
Compile a FIBER decision context (world + query) and report the oracle verdict, omission accounting, and certificate digest faithfully.
Command
Explain the FIBER compile plan — which passes ran, which did NOT run and why, selection ratios, and the omission manifest.
Command
One-pass operational evidence check of the aurora-agent control plane (snapshot, gates, recovery) with honest posture reporting.
Command
Preflight an aurora-agent mission — validate, plan, and show gate posture without dispatching anything.
Command
Validate a FIBER world file — counts, errors, warnings, diagnostics, and the world digest.
Command
Verify a FIBER context-certificate digest (recompute and check the canonical hash).
Skill Claude CodeCodex
Integrate an application with the aurora-agent backend over HTTP or stdio. Use when asked to start or configure the bioprism-api gateway, call the backend from TypeScript or Python, pick between REST and MCP transports, or test MCP wiring without building the Rust binary.
Skill Claude CodeCodex
Set up, build, or troubleshoot the AURORA Agent (bioprism) MCP server used by the aurora-agent plugin. Use when the aurora-agent MCP server fails to start, when its tools are missing from a session, when asked to install or build the aurora-agent backend, or when a bioprism build or test behaves strangely on Windows.
Skill Claude CodeCodex
Compile, layer, compare, and verify FIBER decision contexts with the aurora-agent backend. Use when asked to compile a decision context or world/query pair, judge context-selection strategies against baselines, walk disclosure layers L0 to L4, verify a context certificate, or interpret bioprism CLI envelopes and exit…
Skill Claude CodeCodex
Author, preflight, and execute aurora-agent missions — validated DAGs of MCP tool calls. Use when asked to build or run a mission, when a mission is refused with invalidmission or operationsgateacceptancerequired, when deciding between synchronous agentmission and async submission, or when wiring evaluator reviews and…