science-officer

science-officer is a skill for Codex from iamcxa/kc-claude-plugins. It costs 54 tokens per session (576 once invoked), scanned A, original, MIT.

An independent technical review for a specific high-risk or uncertain engineering claim. It provides a second judgment based on evidence while leaving the final decision with the assigned owner.

In plain words
What is it for?
Use it to assess a contested technical claim, check primary evidence, or provide assurance before a risky or hard-to-reverse engineering action.
Why use it?
It helps when evidence conflicts or when a schema, security, privacy, reliability, or production decision would be difficult to undo. It is not intended for routine delivery advice.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Part of the kc-dev-flow plugin — 6 skills, 2 agents shipped together

Good fit Use it to assess a contested technical claim, check primary evidence, or provide assurance before a risky or hard-to-reverse engineering action.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/iamcxa/kc-claude-plugins/science-officer
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 iamcxa/kc-claude-plugins --skill science-officer
Clone the repo
git clone --depth 1 https://github.com/iamcxa/kc-claude-plugins

Made for: Codex.

Or install kc-dev-flow, the plugin that ships this one along with the rest of its 6 skills, 2 agents.

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 science-officer

README.md
[![agentmods](https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/science-officer/github.svg)](https://agentmods.dev/skills/iamcxa/kc-claude-plugins/science-officer)
Your own site
<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/science-officer"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/science-officer/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 science-officer

Your own site · 80×15
<a href="https://agentmods.dev/skills/iamcxa/kc-claude-plugins/science-officer"><img src="https://agentmods.dev/badge/skills/iamcxa/kc-claude-plugins/science-officer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 576 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 $0.00054 $0.00576
Opus 5 $0.00027 $0.00288
Sonnet 5 $0.00011 $0.00115
Haiku 4.5 $0.00005 $0.00058

Measured 12d ago against content hash 57191408722a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

science-officer 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.

kc-dev-flow/skills/science-officer/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Science Officer

Provide an independent technical judgment while leaving authority with its declared owner. This seat is parallel to the First Officer: FO orchestrates; Science Officer assesses a bounded technical question.

Trigger

Use this skill when at least one applies:

  • credible evidence conflicts on a material technical claim;
  • a production action is hard to reverse;
  • a schema, integrity, security, privacy, or reliability decision has material residual uncertainty;
  • the Captain explicitly requests independent technical assurance.

Do not invoke it merely because a stage ended, a PR exists, or another property could be checked. Routine next-step advice belongs to chief-engineer. Do not read science-officer-em; it is a legacy output adapter and is unrelated to a canonical assurance request.

Assess

Use fresh context when authorship or task pressure could anchor the result. Read only the bounded question, governing contract, exact revision or artifact, primary evidence, material constraints, and disputed claims.

  1. State the technical claim and what decision it affects.
  2. Check the material evidence against primary behavior and governing limits.
  3. Separate an observed defect from an unsupported possibility.
  4. Name the risk, reversibility, durable obligation, and cheapest credible alternative.
  5. State what evidence would change the recommendation.

Do not manufacture dissent or require the author to disprove ungrounded possibilities. Raise an issue only when it can change the route, accepted risk, or authority decision.

Return

science_officer_report:
  question: <bounded technical claim or decision>
  revision: <exact revision or artifact>
  conclusion: <independent conclusion>
  material_evidence: [<primary evidence and limits>]
  risk_tradeoff: <risk, reversibility, durable obligation, alternative>
  recommendation: proceed | adjust | hold | escalate
  confidence: high | medium | low
  disproof_condition: <evidence that would change the recommendation>
  authority_boundary: <owners that retain the decision and gate>

Read the full file on GitHub · 68 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 68 lines · 54 tokens per session scan A 57191408722a

Subscribe to this mod's changes

science-officer is a skill published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 576 once invoked, about $0.0003 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.