honest-figures

honest-figures is a skill for Claude Code from AURORA-NEURO/aurora-agent. It costs 102 tokens per session (1,267 once invoked), scanned A, original, Apache-2.0.

Guidance for making charts and tables traceable and honest, including showing sources, missing results, ties, and negative results clearly.

In plain words
What is it for?
Use it when producing measured-data figures or tables, especially when results must be reproducible, source digests must be retained, and captions should state limitations.
Why use it?
It reduces the risk that figures mislead readers through unsupported numbers, missing data shown as zero, unequal emphasis, or distorted axes.

Skill for Claude Code

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

Part of the aurora-science plugin — 6 skills shipped together

Good fit Use it when producing measured-data figures or tables, especially when results must be reproducible, source digests must be retained, and captions should state limitations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aurora-neuro/aurora-agent/honest-figures
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 honest-figures
Clone the repo
git clone --depth 1 https://github.com/AURORA-NEURO/aurora-agent

Made for: Claude Code.

Or install aurora-science, the plugin that ships this one along with the rest of its 6 skills.

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 honest-figures

README.md
[![agentmods](https://agentmods.dev/badge/skills/aurora-neuro/aurora-agent/honest-figures/github.svg)](https://agentmods.dev/skills/aurora-neuro/aurora-agent/honest-figures)
Your own site
<a href="https://agentmods.dev/skills/aurora-neuro/aurora-agent/honest-figures"><img src="https://agentmods.dev/badge/skills/aurora-neuro/aurora-agent/honest-figures/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 honest-figures

Your own site · 80×15
<a href="https://agentmods.dev/skills/aurora-neuro/aurora-agent/honest-figures"><img src="https://agentmods.dev/badge/skills/aurora-neuro/aurora-agent/honest-figures.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,267 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 $0.00102 $0.01267
Opus 5 $0.00051 $0.00633
Sonnet 5 $0.00020 $0.00253
Haiku 4.5 $0.00010 $0.00127

Measured 12d ago against content hash 7950844ed3df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

honest-figures 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 12d 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-science/skills/honest-figures/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Note: the crate paths, documents, and measured numbers below are illustrations from the aurora-agent workspace where these methods were developed and tested. The methods themselves apply to any figure or table built from measured data.

Honest figures

A figure is a claim with better production values. Everything the workspace enforces about claims — verifiability, refusal-honesty, negative results as results — applies with more force to figures, because figures are what readers remember and what gets screenshotted out of context.

Every figure carries its source digest

A figure should be reproducible from a retained computation, and should say so on its face:

  • Derive figures from digest-bearing artifacts — a certified output's own content hash, a deterministic sweep table (same grid + seed gives byte-identical bytes, asserted by test), a fixture with a pinned digest. Print the digest and the generating command in the caption or the margin.
  • Make regeneration a test with the claim in its name — a_sweep_figure_is_byte_stable_for_a_fixed_table — so a figure that drifts from its data fails a build rather than surviving as a stale image.
  • The workspace's findings document applies the same rule to tables: every number is asserted by a named test, and where a table is transcribed rather than pinned, the document says which rows are reproduced, not pinned and names the command that reprints the source table. A transcription that does not disclose it is a transcription that cannot be audited.

Refused and absent are drawn as refused and absent, never as zero

The comparison harness's JSON omits the judgement keys entirely on a refused row — absence is semantic — and the scoring plane keeps scored, unscored (with a reason), and inapplicable as three distinct states, where an inapplicable cell "is not a zero and does not lower a fixed-input model's average for an action it was never designed to take" (docs/BIOEVAL_PLANE_AUDIT.md). A renderer is where that discipline usually dies: a chart library coerces a missing value to zero, and a refusal becomes the shortest bar — visually, the cheapest attempt.

Read the full file on GitHub · 97 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. 12d ago First seen · 97 lines · 102 tokens per session scan A 7950844ed3df

Subscribe to this mod's changes

honest-figures is a skill published in the GitHub repository AURORA-NEURO/aurora-agent (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 102 tokens to every session and 1,267 once invoked, about $0.0005 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

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

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