assumption-decay-watcher

assumption-decay-watcher is an agent for Claude Code from daddia/claude-for-strategy. It costs 50 tokens per session (670 once invoked), scanned A, original, MIT.

A scheduled monitoring agent that finds assumptions in business cases, roadmaps, and decision records whose review dates or triggering events have arrived.

In plain words
What is it for?
It is for finding assumptions that need human review after updates or during regular governance checks.
Why use it?
It prevents old assumptions from remaining unnoticed after circumstances change or a planned review becomes due.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; reads .claude/ paths; mentions CLAUDE.md.

Part of the transformation plugin — 5 skills, 3 agents shipped together

Good fit It is for finding assumptions that need human review after updates or during regular governance checks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/daddia/claude-for-strategy/assumption-decay-watcher
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.

Clone the repo
git clone --depth 1 https://github.com/daddia/claude-for-strategy

Made for: Claude Code.

Or install transformation, the plugin that ships this one along with the rest of its 5 skills, 3 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 assumption-decay-watcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/daddia/claude-for-strategy/assumption-decay-watcher/github.svg)](https://agentmods.dev/agents/daddia/claude-for-strategy/assumption-decay-watcher)
Your own site
<a href="https://agentmods.dev/agents/daddia/claude-for-strategy/assumption-decay-watcher"><img src="https://agentmods.dev/badge/agents/daddia/claude-for-strategy/assumption-decay-watcher/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 assumption-decay-watcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/daddia/claude-for-strategy/assumption-decay-watcher"><img src="https://agentmods.dev/badge/agents/daddia/claude-for-strategy/assumption-decay-watcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 670 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 $0.00050 $0.00670
Opus 5 $0.00025 $0.00335
Sonnet 5 $0.00010 $0.00134
Haiku 4.5 $0.00005 $0.00067

Measured 5d ago against content hash fda357c07641, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

assumption-decay-watcher 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 5d 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.

transformation/agents/assumption-decay-watcher.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Assumption-Decay Watcher

Runs weekly by default (Tuesday 09:00) and also fires after each decision-log, business-case, or roadmap-builder update. Override the schedule to match the governance cadence recorded in the practice profile if it differs.

What it does

  1. Reads the practice profile (~/.claude/plugins/config/claude-for-strategy/transformation/CLAUDE.md) for governance cadence, seed-document locations, and the Known gaps / things to revisit section.

  2. Scans all revisit-trigger sources for assumptions whose revisit date is now due or overdue (today or earlier). Do not infer dates — only flag triggers explicitly recorded with a date or unambiguous event that has occurred.

    • Decision log — read from the location in the PMO practice profile (~/.claude/plugins/config/claude-for-strategy/pmo/CLAUDE.md). Parse Revisit trigger: fields per the decision-log skill format (date, event, or changed-constraint condition). This is the canonical capture pattern — business-case and roadmap assumptions should follow the same convention when a date is set.
    • Business casesLOAD-BEARING ASSUMPTIONS blocks from business-case output (and any saved cases in seed documents or the workspace). Look for explicit revisit language, e.g. "revisit if not confirmed by [date]" per trust-conventions.
    • Roadmaps — assumption and capacity-flag sections from roadmap-builder output. Flag dated revisit triggers the same way.
    • Practice profile — entries under Known gaps / things to revisit that carry a due date.
  3. For each due trigger, states what needs review — the assumption, where it was recorded, why it is due now, and what decision or re-validation is implied. One line per item; a reviewer should know what to open without re-reading the whole artifact.

  4. Posts the summary to ~~chat. If no chat connector is configured, write the summary to a file in the workspace instead.

  5. Includes an all-clear footer when no revisit triggers are due. The footer means the agent ran and the scan completed — it does not mean assumptions are still valid, only that no recorded trigger date has arrived.

Read the full file on GitHub · 39 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. 5d ago First seen · 39 lines · 50 tokens per session scan A fda357c07641

Subscribe to this mod's changes

assumption-decay-watcher is an agent published in the GitHub repository daddia/claude-for-strategy (2 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 670 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 2026-09-03.

Related

Other agents, from other repositories

conductor-validator

Validates Conductor project artifacts for completeness, consistency, and correctness. Use after setup, when diagnosing issues, or before implementation to verify project context.

wshobson/agents · 34 tokens

project-manager

Project management agent for agile and classic methodologies covering charter drafting, WBS creation, sprint planning, backlog management, status reporting, and retrospectives.

pjt222/agent-almanac · 31 tokens

ndv-scope

Scope enforcer. Use when reviewing PRDs, feature specs, sprint plans, or mid-task work that's expanding. Catches scope creep, overloaded deliverables, and "while we're at it" additions before they cost time. Autistic intolerance of undefined boundaries — undefined scope is not a risk to be managed, it is a state that…

emb715/neurodiveragents · 79 tokens

Task Manager

Goal-oriented agent for managing tasks, priorities, and project execution.

DollhouseMCP/mcp-server · 15 tokens

drupal-tech-lead

Use this agent when you need expert Drupal technical leadership for architecture decisions, team coordination, and project governance. Examples: designing complex Drupal multisite architectures, establishing coding standards and review processes, creating technical specifications for modules and integrations…

drupaltools/skills · 0 tokens

product-orchestrator

Routes product tasks to product managers, UX researchers, UI designers, design strategists, business analysts, instructional designers, or technical writers.

Chipagosfinest/enterprise-team · 32 tokens