assumptions

assumptions is a skill for Claude Code, Codex from Kastalien-Research/thoughtbox. It costs 32 tokens per session (919 once invoked), scanned A, original, MIT.

A registry for recording beliefs about dependencies, tools, the environment, or how a system behaves, along with evidence and verification details.

In plain words
What is it for?
Use it to list assumptions, add new records, verify whether a claim is still true, and track the impact when one is wrong.
Why use it?
It prevents the team from repeatedly rediscovering known failures and makes uncertain information easier to review.

Skill for Claude CodeCodex

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/kastalien-research/thoughtbox/assumptions
Any agent
npx skills add Kastalien-Research/thoughtbox --skill assumptions
Clone the repo
git clone --depth 1 https://github.com/Kastalien-Research/thoughtbox

Made for: Claude Code, Codex.

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 assumptions

README.md
[![agentmods](https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/assumptions.svg)](https://agentmods.dev/skills/kastalien-research/thoughtbox/assumptions)
Your own site
<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/assumptions"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/assumptions.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 919 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 5.1 $0.00032 $0.00919
Opus 5 $0.00016 $0.00460
Sonnet 5 $0.00006 $0.00184
Haiku 4.5 $0.00003 $0.00092

Measured 5d ago against content hash dd7607981f4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

assumptions 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.

.agents/skills/assumptions/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Manage assumptions: $ARGUMENTS

Commands

Parse the first word of $ARGUMENTS to determine the command:

list — Show all tracked assumptions

  1. Read all .assumptions/*.jsonl files
  2. Parse each line as a JSON record
  3. Display sorted by confidence (lowest first) or staleness (oldest verification first)
  4. Format as a table: ID | Category | Claim | Confidence | Last Verified | Status

add — Register a new assumption

Parse remaining arguments for: --category, --claim, --evidence, --source

Create a new assumption record in .assumptions/registry.jsonl:

{
  "id": "<category>-<short-slug>",
  "category": "<api|dependency|behavior|environment|tooling>",
  "claim": "<what we assume to be true>",
  "evidence": "<what supports this assumption>",
  "source": "<where this was discovered>",
  "confidence": 0.8,
  "created": "<ISO 8601>",
  "last_verified": "<ISO 8601>",
  "verification_method": "<how to test this>",
  "failure_history": [],
  "status": "active",
  "blast_radius": "<what breaks if this assumption is wrong>"
}

verify — Re-verify an assumption

  1. Read the assumption record by ID
  2. Execute the verification method (may involve web search, API calls, or code checks)
  3. Update last_verified timestamp and confidence score
  4. If verification fails, add to failure_history and reduce confidence
  5. If confidence drops below 0.3, mark status as suspect and warn

stale — Show assumptions that need re-verification

  1. Read all assumption records
  2. Filter to those where last_verified is more than 14 days ago
  3. Sort by blast_radius (highest first)
  4. Display with suggested verification actions

seed — Seed registry from MEMORY.md gotchas

  1. Read MEMORY.md
  2. Extract entries from "Gotchas", "Known Bugs", and "MCP Knowledge API Gotchas" sections
  3. For each entry, create an assumption record with:
    • category: inferred from content (api, dependency, behavior, etc.)
    • claim: the gotcha statement
    • evidence: "Discovered empirically" + date from MEMORY.md
    • confidence: 0.9 (verified by experience)
    • verification_method: suggested test

Read the full file on GitHub · 98 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 · 98 lines · 32 tokens per session scan A dd7607981f4e

Subscribe to this mod's changes

assumptions is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 919 once invoked, about $0.0002 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

forget

Delete specific observations from agentmemory after showing them and getting explicit confirmation. Use when the user says "forget this", "delete memory", "remove that note", or wants to scrub specific data for privacy.

rohitg00/agentmemory · 43 tokens

handoff

Resume the most recent agent session for the current working directory, leading with any unanswered question. Use when the user says "where were we", "resume", "handoff", "pick up where I left off", or starts a session with no fresh context.

rohitg00/agentmemory · 55 tokens

agentmemory-agents

How agentmemory wires into host coding agents via the connect command. Use when installing agentmemory into a specific agent, when asked which agents are supported, or when a connect adapter writes the wrong config path.

rohitg00/agentmemory · 46 tokens

agentmemory-config

Skill "agentmemory-config" from rohitg00/agentmemory, covering quick start, defaults worth knowing, ports, see also and reference.

rohitg00/agentmemory · 44 tokens

agentmemory-hooks

The agentmemory plugin hooks that capture observations automatically across the agent session lifecycle. Use when explaining how memory gets captured without manual saves, when debugging missing observations, or when tuning what gets recorded.

rohitg00/agentmemory · 42 tokens

session-history

Show what happened in recent past sessions on this project as a clean timeline. Use when the user asks "what did we do last time", "session history", "past sessions", or wants an overview of previous work.

rohitg00/agentmemory · 47 tokens