32-trust-posture

32-trust-posture is a skill for Claude Code from terrene-foundation/kailash-coc-claude-py. It costs 39 tokens per session (1,006 once invoked), scanned C, original, Apache-2.0.

A guide for assigning graduated trust levels to implementation rules, from automatic blocking to warnings and later review. It explains how rules should behave during coding, auditing, and security testing.

In plain words
What is it for?
Use it when authoring rules, setting audit depth, reviewing violations, or deciding whether a security rule should change its trust level.
Why use it?
It helps teams decide when a rule should stop an action, report it, warn about it, or record it for later investigation.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths.

Good fit Use it when authoring rules, setting audit depth, reviewing violations, or deciding whether a security rule should change its trust level.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/terrene-foundation/kailash-coc-claude-py/32-trust-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.

Any agent
npx skills add terrene-foundation/kailash-coc-claude-py --skill 32-trust-posture
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 32-trust-posture

README.md
[![agentmods](https://agentmods.dev/badge/skills/terrene-foundation/kailash-coc-claude-py/32-trust-posture/github.svg)](https://agentmods.dev/skills/terrene-foundation/kailash-coc-claude-py/32-trust-posture)
Your own site
<a href="https://agentmods.dev/skills/terrene-foundation/kailash-coc-claude-py/32-trust-posture"><img src="https://agentmods.dev/badge/skills/terrene-foundation/kailash-coc-claude-py/32-trust-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 32-trust-posture

Your own site · 80×15
<a href="https://agentmods.dev/skills/terrene-foundation/kailash-coc-claude-py/32-trust-posture"><img src="https://agentmods.dev/badge/skills/terrene-foundation/kailash-coc-claude-py/32-trust-posture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,006 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00039 $0.01006
Opus 5 $0.00019 $0.00503
Sonnet 5 $0.00008 $0.00201
Haiku 4.5 $0.00004 $0.00101

Measured 8d ago against content hash 8b1c1b630137, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

32-trust-posture scanned grade C with 1 finding 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 8d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

| Destructive + reversible (rm -rf in tmp dir) | PreToolUse | `block` |
.claude/skills/32-trust-posture/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trust Posture — Implementation Skill

The contract is rules/trust-posture.md. This skill is the how — what /codify, /redteam, /implement, and rule authors do to wire a rule into the graduated-trust loop.

When to load this skill

  • Authoring a new rule (anywhere in /codify)
  • Designing audit depth (/redteam)
  • Interpreting gate behavior (/implement halts, /sweep reports)
  • Reading or recommending a posture change (/posture, posture-auditor agent)
  • Reviewing whether a violation pattern should trigger automatic downgrade

If your task is none of the above, this skill is not for you.

The five-question rule-authoring checklist

Every rule authored by /codify MUST answer these in a "Trust Posture Wiring" section. See rule-authoring-checklist.md for the canonical format.

  1. Severityblock / halt-and-report / advisory / post-mortem. Use block only when the action MUST be physically prevented (PreToolUse + destructive). Use halt-and-report when the action already happened but the agent must surface and wait. Use advisory for soft warnings. Use post-mortem for Stop-class detections (forensic only, surfaces next session).
  2. Grace period — 0 days (rule is teeth-from-day-one), 7 days (standard for newly codified rules), 30 days (large surface change requiring migration time). During grace, the rule is in pending_verification; SessionStart announces it; violations trigger regression_within_grace.
  3. Receipt requirement — does the rule warrant [ack: <rule_id>] from the agent in the first response of every new session? Reserve for high-stakes rules where evidence shows the agent ignores SessionStart context.
  4. Cumulative threshold — default 3× same-rule in 30 days = 1 posture downgrade. Override only if the rule's failure mode is so severe that 1× should emergency-downgrade (e.g., destructive bash without confirm, secret leak).
  5. Detection mechanism — regex (lexical), AST (structural), behavioral (cross-reference), or human-only. Lexical alone is advisory/post-mortem. Auto-downgrade requires structural or behavioral signal.

Read the full file on GitHub · 58 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 58 lines · 39 tokens per session scan C 8b1c1b630137

Subscribe to this mod's changes

32-trust-posture is a skill published in the GitHub repository terrene-foundation/kailash-coc-claude-py (12 stars, last pushed 24d ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,006 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens