understand-state

understand-state is a skill for Claude Code, Codex from ai-swiss/base. It costs 40 tokens per session (610 once invoked), scanned A, original, Apache-2.0.

A skill for understanding a project's current state before changing code. It compares the written requirements with test evidence, project decisions, and the implementation.

In plain words
What is it for?
Use it to inspect specifications, check the requirements matrix, confirm behavior in code, and identify the most valuable next change.
Why use it?
It prevents agents from treating an old plan or review as the truth and shows what is proven, uncertain, or still missing.

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/ai-swiss/base/understand-state
Any agent
npx skills add ai-swiss/base --skill understand-state
Clone the repo
git clone --depth 1 https://github.com/ai-swiss/base

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 understand-state

README.md
[![agentmods](https://agentmods.dev/badge/skills/ai-swiss/base/understand-state.svg)](https://agentmods.dev/skills/ai-swiss/base/understand-state)
Your own site
<a href="https://agentmods.dev/skills/ai-swiss/base/understand-state"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/understand-state.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 610 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 $0.00040 $0.00610
Opus 5 $0.00020 $0.00305
Sonnet 5 $0.00008 $0.00122
Haiku 4.5 $0.00004 $0.00061

Measured 5d ago against content hash 9910eecd2cdb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

understand-state 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.

.ai/agents/base-contributor/skills/processes/understand-state/SKILL.md · 51 lines

What it actually says

Understand the state

Orient before touching anything. The reading order is fixed: specs/ first, then the code, never a plan or a review (see specs/current/00_overview/les-deux-plans.md).

Steps

  1. Read the truth plane. Open specs/current/10_core/requirements.md (the ID index) and the chapter leaf for the area in question. This is what BASE requires.
  2. Read the proof. Open specs/current/10_core/requirements-matrix.md (generated). The /⚠️/ column tells you which requirements are proven, weakly proven, or unproven. Run npm run spec:matrix to regenerate it if in doubt.
  3. Read the change plane. Skim decisions/index.md for the durable choices and any open change record. This is why things are the way they are.
  4. Confirm against the code. For a behaviour, read the function named normative in the leaf; the regeneration bar is: could the code be rebuilt from the spec plus its tests?
  5. Report the state and the next step. Name what is solid, what is ⚠️/, and the single most valuable next change. Hand off to plan (consequential) or implement (obvious).

What you never do

  • Treat a plan or a review as current truth.
  • Invent a state you did not read; cite file:line or command output.
  • Drift into auditing a user's BASE project — that is a different agent.
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 · 51 lines · 40 tokens per session scan A 9910eecd2cdb

Subscribe to this mod's changes

understand-state is a skill published in the GitHub repository ai-swiss/base (43 stars, last pushed yesterday), licensed Apache-2.0. It adds 40 tokens to every session and 610 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