declaring-intent

A written statement of what an agent plans to do before a critical or irreversible action. It records the reason, expected result, conditions for stopping, and rollback plan.

In plain words
What is it for?
Use it to prepare and review deploys, migrations, trust-related changes, and public claims with clear preconditions and recovery steps.
Why use it?
It lets a reviewer question the reasoning before a deploy, migration, public claim, or other high-consequence change happens.

Skill for Claude CodeCodex

Part of the nuclear-grade plugin — 24 skills, 28 commands, 5 agents shipped together

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.

agentmods
npx agentmods add skills/flyfission/nuclear-grade-context-engineering/declaring-intent
Any agent
npx skills add FlyFission/nuclear-grade-context-engineering --skill declaring-intent
Clone the repo
git clone --depth 1 https://github.com/FlyFission/nuclear-grade-context-engineering

Made for: Claude Code, Codex.

Or install nuclear-grade, the plugin that ships this one along with the rest of its 24 skills, 28 commands, 5 agents.

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,329 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00082 $0.01329
Opus 5 $0.00041 $0.00665
Sonnet 5 $0.00016 $0.00266
Haiku 4.5 $0.00008 $0.00133

Measured 3d ago against content hash c68791d9aae1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

declaring-intent 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 3d 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/declaring-intent/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Declaring Intent

Overview

Before a critical action, say what you intend to do and the reasoning behind it, then act unless someone stops you. The value is that a reviewer can challenge the thinking before the action happens, not the wreckage after. The declaration also forces the actor to make the "why" and the "how will I know" explicit. For an agent, the stated intent is a proposal to be reviewed, never evidence that the agent actually understood.

Decision contract

  • Claim checked: the declared intent names a falsifying signal (not just success), carries concrete abort criteria and a checked rollback, and the preconditions are proven rather than assumed before the action runs.
  • Artifact observed: the intended action and target, the reasoning and precondition evidence, the expected result, and the abort/rollback criteria -> an intent declaration or intent.md (action, reasoning, expected result, abort, rollback, decision rights, backup) and the actual-vs-expected result.
  • Decision affected: block -- whether a reviewer clears the critical or irreversible action before it runs, given expected result, abort criteria, and rollback.
  • Failure class: unfalsifiable-intent (a stated goal with no falsifying signal, abort threshold, or verified rollback).
  • Next action: stop when no rollback exists or abort criteria are unmeasurable; get a second reviewer when only one has seen the reasoning.

When to Use

  • Before a deploy, migration, data change, public claim, dependency or model swap, or release.
  • When an action is hard to reverse, or its blast radius is more than the immediate file.
  • When you want a reviewer's eyes on the reasoning and the abort criteria before execution.
  • When standing authority lets an agent proceed unless told no, and the team needs the "no" window.

When Not to Use

  • The action is a routine, reversible edit with obvious proof and no trust boundary.
  • An incident is live and the next move is stabilization, not a fresh proposal.
  • Someone wants the declaration treated as a guarantee or certification.

Read the full file on GitHub · 107 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. 3d ago First seen · 107 lines · 82 tokens per session scan A c68791d9aae1

Subscribe to this mod's changes

declaring-intent is a skill published in the GitHub repository FlyFission/nuclear-grade-context-engineering (33 stars, last pushed 24d ago), licensed MIT. It adds 82 tokens to every session and 1,329 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 2026-08-30.

Related

Other skills, from other repositories

contextlock

Safely inspect a repository through the ContextLock MCP server. Use when exploring, searching, reviewing, or auditing repository files with ContextLock, especially before reading unfamiliar code or when sensitive files and secrets may be present.

LutaElbert/contextlock · 46 tokens

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

doca-compress

Use this skill for hands-on DOCA Compress programming on a BlueField DPU, ConnectX NIC, or host with DOCA — enabling compress-deflate, decompress-deflate, decompress-lz4-stream, or decompress-lz4-block tasks on a docacompress context (the hardware supports DEFLATE both directions plus LZ4 decompress; LZ4 encode is NOT…

NVIDIA/skills · 242 tokens

git-ai-search

Search and restore AI conversation context from git history.

git-ai-project/git-ai · 13 tokens