fiber-decision-context

fiber-decision-context is a skill for Claude Code from AURORA-NEURO/aurora-agent. It costs 71 tokens per session (937 once invoked), scanned A, original, Apache-2.0.

A guide for compiling and checking FIBER decision contexts with the AURORA Agent backend. A decision context is the set of facts selected for a decision, and its certificate records what was left out and whether that could matter.

In plain words
What is it for?
Use it to validate worlds and queries, compile or refine contexts, compare selection strategies, inspect disclosure layers, and verify context certificates.
Why use it?
It makes context selection and omissions inspectable instead of leaving the agent to rely on an unexplained subset of information.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the aurora-agent plugin — 4 skills, 7 commands, 1 agent shipped together

Good fit Use it to validate worlds and queries, compile or refine contexts, compare selection strategies, inspect disclosure layers, and verify context certificates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aurora-neuro/aurora-agent/fiber-decision-context
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.

Any agent
npx skills add AURORA-NEURO/aurora-agent --skill fiber-decision-context
Clone the repo
git clone --depth 1 https://github.com/AURORA-NEURO/aurora-agent

Made for: Claude Code.

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.

agentmods badge for fiber-decision-context

README.md
[![agentmods](https://agentmods.dev/badge/skills/aurora-neuro/aurora-agent/fiber-decision-context/github.svg)](https://agentmods.dev/skills/aurora-neuro/aurora-agent/fiber-decision-context)
Your own site
<a href="https://agentmods.dev/skills/aurora-neuro/aurora-agent/fiber-decision-context"><img src="https://agentmods.dev/badge/skills/aurora-neuro/aurora-agent/fiber-decision-context/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fiber-decision-context

Your own site · 80×15
<a href="https://agentmods.dev/skills/aurora-neuro/aurora-agent/fiber-decision-context"><img src="https://agentmods.dev/badge/skills/aurora-neuro/aurora-agent/fiber-decision-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 937 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00071 $0.00937
Opus 5 $0.00036 $0.00468
Sonnet 5 $0.00014 $0.00187
Haiku 4.5 $0.00007 $0.00094

Measured 10d ago against content hash df693911088c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

fiber-decision-context 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 10d 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/skills/fiber-decision-context/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

FIBER decision contexts

FIBER compiles a world (typed facts + factors) and a query into a Decision Section plus a Context Certificate — a receipt stating exactly what was omitted and whether it could have changed the decision. Omissions are reported at every layer: layering hides volume, never the fact of an omission.

Where things are

  • Checkout: $AURORA_AGENT_ROOT~/aurora-agent~/bioprism.
  • CLI: <root>/target/release/bioprism(.exe); run from the checkout root.
  • MCP tools (if the aurora-backend plugin is installed): fiber_compile, fiber_refine, fiber_explain, fiber_verify, context_compare, world_validate — same Rust implementation as the CLI.
  • Reference fixtures: world fixtures/fiber-v0.1/radiogenomic_world.json, query fixtures/fiber-v0.1/leakage_query.json. On this pair the reference certificate digest is c0da17ffc80465258345c8a538171bfd868100cd883e9a20780a0dc5477e7ea4 — a checkable expectation: three independent implementations (CPython, eager Rust, indexed store) agree on it byte for byte.

The workflow

  1. Validate the world (world validate --world W; no --query flag).
  2. Explain the plan (context explain) — always surface the passes that did NOT run with their verbatim reasons, and the omission manifest.
  3. Compile (context compile [--certificate-out C]). The oracle status invalid means the oracle found integrity violations in the data (e.g. identity/site/temporal/preprocessing leakage) — that is the finding, not a failure. Report witnesses verbatim.
  4. Layer via MCP fiber_compile with layer: L0..L4 — L0 is the smallest honest layer (~200 estimated tokens on the reference pair vs ~1,900 full); each result carries a content-addressed refinement handle for fiber_refine. estimated_tokens.method self-discloses that it is a heuristic, not a tokenizer — quote it when reporting token numbers.
  5. Compare (context compare) — judge strategies by verdict_preserving, never by status alone: a "valid" from a non-preserving strategy is a FALSE verdict. Report cheapest_admissible_strategy verbatim even when it is a baseline (on the reference pair it is graph-5-hop — an honest negative the project publishes deliberately).
  6. Verify (context verify --certificate C) — certificates verify without the engine that produced them.

Read the full file on GitHub · 70 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. 10d ago First seen · 70 lines · 71 tokens per session scan A df693911088c

Subscribe to this mod's changes

fiber-decision-context is a skill published in the GitHub repository AURORA-NEURO/aurora-agent (1 stars, last pushed today), licensed Apache-2.0. It adds 71 tokens to every session and 937 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

halopsa

Every HaloPSA, HaloITSM and HaloCRM feature, plus a local SQLite store and cross-entity views the API can't return. Trigger phrases: triage my Halo queue, check SLA breaches in HaloPSA, who is overloaded in Halo, client card for Acme in Halo, Halo contract burn-down, what changed in Halo since this morning, find time…

Servosity/msp-skills · 104 tokens

veeam

Use when the user asks to check Veeam backup health across customers, find failing or stale backup jobs, surface workloads past their RPO, triage VSPC alarms, or report per-tenant license usage from a Veeam Service Provider Console. Syncs every tenant into a local SQLite mirror so it answers multi-tenant backup…

Servosity/msp-skills · 136 tokens

cipp

First single-binary CLI for CIPP - offline SQLite store, fleet posture analytics, and cross-tenant fan-out no other CIPP tool has. Trigger phrases: check MFA across all my tenants, find unused M365 licenses, offboard users from a CSV in CIPP, which tenants drifted off baseline, list CIPP tenants, use cipp, run…

Servosity/msp-skills · 89 tokens

appdirect

Every documented AppDirect marketplace operation in one binary, plus offline sync and billing-reconciliation joins. Trigger phrases: reconcile appdirect billing, which appdirect payments failed this week, what changed in appdirect subscriptions, show my appdirect pipeline, appdirect company 360, use appdirect, run…

Servosity/msp-skills · 74 tokens

connectwise-manage

Every ConnectWise PSA workflow from the terminal - with a typed conditions query builder, offline SQLite sync, and cross-entity views (unbilled work, account 360, board triage) the PSA web UI can't give you. Trigger phrases: list connectwise tickets, triage the help desk board, find unbilled time in connectwise…

Servosity/msp-skills · 115 tokens

immybot

Every ImmyBot endpoint typed, plus a local SQLite mirror that answers the cross-tenant questions the web UI cannot. Trigger phrases: what failed in last night's maintenance window, which tenants are still on an old version of chrome, why didn't this computer get the deployment, what changed in the fleet since…

Servosity/msp-skills · 97 tokens