staying-on-mission

staying-on-mission is a skill for Claude Code from FlyFission/nuclear-grade-context-engineering. It costs 90 tokens per session (2,153 once invoked), scanned A, original, MIT.

A guide for keeping coding work tied to a written mission, including its goal, success criteria, and non-goals. It requires a deliberate choice when the work drifts, such as re-anchoring, escalating, or stopping.

In plain words
What is it for?
Use it when an agent keeps working after the task has changed, when scope is expanding, or when progress is looping. It helps decide whether to continue, clarify ownership, or stop.
Why use it?
It prevents scope creep, repeated actions, and gradual drops in standards from replacing the original purpose. The written anchor makes it easier to judge whether each action still matters.

Skill for Claude Code

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

Part of the nuclear-grade plugin — 29 skills, 28 commands, 5 agents shipped together

Good fit Use it when an agent keeps working after the task has changed, when scope is expanding, or when progress is looping. It helps decide whether to continue, clarify ownership, or stop.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/flyfission/nuclear-grade-context-engineering/staying-on-mission
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 FlyFission/nuclear-grade-context-engineering --skill staying-on-mission
Clone the repo
git clone --depth 1 https://github.com/FlyFission/nuclear-grade-context-engineering

Made for: Claude Code.

Or install nuclear-grade, the plugin that ships this one along with the rest of its 29 skills, 28 commands, 5 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 staying-on-mission

README.md
[![agentmods](https://agentmods.dev/badge/skills/flyfission/nuclear-grade-context-engineering/staying-on-mission/github.svg)](https://agentmods.dev/skills/flyfission/nuclear-grade-context-engineering/staying-on-mission)
Your own site
<a href="https://agentmods.dev/skills/flyfission/nuclear-grade-context-engineering/staying-on-mission"><img src="https://agentmods.dev/badge/skills/flyfission/nuclear-grade-context-engineering/staying-on-mission/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 staying-on-mission

Your own site · 80×15
<a href="https://agentmods.dev/skills/flyfission/nuclear-grade-context-engineering/staying-on-mission"><img src="https://agentmods.dev/badge/skills/flyfission/nuclear-grade-context-engineering/staying-on-mission.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,153 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00090 $0.02153
Opus 5 $0.00045 $0.01077
Sonnet 5 $0.00018 $0.00431
Haiku 4.5 $0.00009 $0.00215

Measured 10d ago against content hash 5aab0b535ebe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

staying-on-mission 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.

skills/staying-on-mission/SKILL.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Staying on Mission

Overview

Mission drift is when an agent keeps shipping work that no longer serves the original goal. It comes in two forms. The first is intent drift: scope creeps, the goal quietly gets swapped for a smaller one, or the agent wins the task but loses the mission. The second is standards drift: the work gets a little less careful each time you accept one more small exception. Letting a bad habit become normal this way is called the normalization of deviance.

This skill keeps a written mission anchor in front of the work. When an action stops serving that anchor, you make one of three choices: re-anchor, escalate, or stop. The anchor has three parts: the goal, the success criteria (how you know you are done), and the clear non-goals (what you are deliberately not doing). One named person owns the anchor. That person is responsible for whether this change still serves its mission. Every small action still has to trace back to that larger mission.

The anchor is also the clarity that lets authority move to the edge: it is the commander's intent that keeps a decentralized decision aligned with the goal. Push decisions to where the information is, but only against a clear, shared anchor — otherwise local wins quietly drift from the mission.

Decision contract

  • Claim checked: the current action was tested against the written anchor's goal, success criteria, and non-goals, the loop and attempt count were actually run, and any crossed non-goal or loosened standard has a justification row, not a quiet edit.
  • Artifact observed: the written anchor (.nuclear/mission.md, ## Mission anchor in risk.md, or .nuclear/charter.md) and the current action/diff -> a recorded continue/re-anchor/escalate/stop decision, updated anchor, and any justification row.
  • Decision affected: block -- continue / re-anchor / escalate / stop, plus the restated goal anchor.
  • Failure class: mission-drift (an action serving a swapped-in goal, a crossed non-goal, or a standard loosened "just this once").
  • Next action: stop and return to the anchor when a non-goal would be crossed with no justification; 3 failed attempts or scope you cannot check escalates to the owner.

Read the full file on GitHub · 131 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 · 131 lines · 90 tokens per session scan A 5aab0b535ebe

Subscribe to this mod's changes

staying-on-mission is a skill published in the GitHub repository FlyFission/nuclear-grade-context-engineering (33 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 2,153 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 2026-08-30.