posture

posture is a command for Claude Code from terrene-foundation/kailash-coc-claude-py. It costs 35 tokens per session (1,876 once invoked), scanned A, original, Apache-2.0.

A repository trust-management command with five autonomy levels, from limited assistance to delegated operation. It shows trust history and can change the allowed level after a verification challenge.

In plain words
What is it for?
Use it to inspect the current trust level, review transitions and violations, initialize posture state, or request a controlled upgrade or override.
Why use it?
It makes the amount of autonomy granted to an AI or operator visible and prevents silent changes to repository permissions.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

Good fit Use it to inspect the current trust level, review transitions and violations, initialize posture state, or request a controlled upgrade or override.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/terrene-foundation/kailash-coc-claude-py/posture
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/terrene-foundation/kailash-coc-claude-py

Made for: Claude Code.

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 posture

README.md
[![agentmods](https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/posture/github.svg)](https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/posture)
Your own site
<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/posture"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/posture/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 posture

Your own site · 80×15
<a href="https://agentmods.dev/commands/terrene-foundation/kailash-coc-claude-py/posture"><img src="https://agentmods.dev/badge/commands/terrene-foundation/kailash-coc-claude-py/posture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,876 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 $0.00035 $0.01876
Opus 5 $0.00017 $0.00938
Sonnet 5 $0.00007 $0.00375
Haiku 4.5 $0.00003 $0.00188

Measured 9d ago against content hash 8ecf80512b3f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

posture 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 9d 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.

.claude/commands/posture.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/posture — Trust Posture Management

The graduated-trust-posture system (rules/trust-posture.md + skills/32-trust-posture/) defines five autonomy levels per repo. This command surfaces and changes posture state.

State lives at <main_checkout>/.claude/learning/posture.json (per skills/32-trust-posture/posture-spec.md). Direct edits are blocked by settings.json::permissions.deny.

Subcommands

/posture (no args) — show current

Read posture.json and report:

  • Current posture for THIS operator (L1_PSEUDO_AGENT … L5_DELEGATED)
  • Operative posture = min(operator_posture, repo_floor) per posture-v2.js::computeOperativePosture
  • repo_floor (the shared constraint across all operators)
  • Time at current posture (e.g., "3 days 14h")
  • Pending verification entries (rule_id, day N of grace, regression-within-grace policy)
  • Last 5 own transitions with type + reason
  • Last 10 own violations (rule_id, severity, evidence head, addressed_by)
  • Fresh-repo flag, fail-closed flag (if applicable)
  • Genesis-generation partition signal (degrades to L3 if partitioned)

Multi-operator surface (C2): if the invoking operator has role owner or senior, the report ALSO lists every other operator's operative posture (read-only view; cross-operator postures are otherwise siloed by posture-v2.js's operator partition). Contributor- role operators see only their own posture.

Output is plain markdown — no state mutation.

/posture init — initialize fresh repo

Used once on a repo that has never run the trust system. Writes posture.json with posture: L5_DELEGATED + creates .initialized marker. Refuses to run if .initialized already exists (use /posture override to change posture on an initialized repo).

/posture history [--all | --recent N] — transition log

Reads transition_history from posture.json. Defaults to last 10 transitions. Each row: from → to, type, reason, ts, approved_by. --all dumps every transition since INIT.

/posture violations [--rule X | --since DATE | --limit N] — violation log

Read the full file on GitHub · 136 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. 9d ago First seen · 136 lines · 35 tokens per session scan A 8ecf80512b3f

Subscribe to this mod's changes

posture is a command published in the GitHub repository terrene-foundation/kailash-coc-claude-py (12 stars, last pushed 24d ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,876 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 2026-09-03.