powershell-exact-action

powershell-exact-action is a skill for Claude Code, Codex from Chisiki1/objective-integrity-framework. It costs 79 tokens per session (483 once invoked), scanned A, original, Apache-2.0.

A final mechanical check for a completed PowerShell command or batch member from a registered recurring command pattern. It runs only after defaults, JSON, expansion, and quoting are finished, and does not prove that the command is semantically correct or will work at runtime.

In plain words
What is it for?
Use it to preflight finalized PowerShell commands and expanded command batches before execution.
Why use it?
It catches certain repeatable command-shape problems before a PowerShell action, without confusing that check with a full review or test.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: $skill-name invocation.

Good fit Use it to preflight finalized PowerShell commands and expanded command batches before execution.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chisiki1/objective-integrity-framework/powershell-exact-action
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 Chisiki1/objective-integrity-framework --skill powershell-exact-action
Clone the repo
git clone --depth 1 https://github.com/Chisiki1/objective-integrity-framework

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 powershell-exact-action

README.md
[![agentmods](https://agentmods.dev/badge/skills/chisiki1/objective-integrity-framework/powershell-exact-action/github.svg)](https://agentmods.dev/skills/chisiki1/objective-integrity-framework/powershell-exact-action)
Your own site
<a href="https://agentmods.dev/skills/chisiki1/objective-integrity-framework/powershell-exact-action"><img src="https://agentmods.dev/badge/skills/chisiki1/objective-integrity-framework/powershell-exact-action/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 powershell-exact-action

Your own site · 80×15
<a href="https://agentmods.dev/skills/chisiki1/objective-integrity-framework/powershell-exact-action"><img src="https://agentmods.dev/badge/skills/chisiki1/objective-integrity-framework/powershell-exact-action.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 483 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 $0.00079 $0.00483
Opus 5.5 $0.00032 $0.00193
Sonnet 5.5 $0.00016 $0.00097
Haiku 4.5 $0.00008 $0.00048

Measured 1mo ago against content hash 0f81177f957c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

powershell-exact-action 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 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/Test-PowerShellExactAction.ps1), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

runtime/skills/powershell-exact-action/SKILL.md · 20 lines

What it actually says

PowerShell Exact-Action Preflight

Use this skill only on the exact finalized PowerShell representation that would otherwise be submitted.

  1. For one command, run powershell -NoProfile -File scripts/Test-PowerShellExactAction.ps1 -CommandText '<exact text>' -IncludeSource using a transport that preserves the literal command. For a batch, supply -InputJsonPath containing { "members": [{"id":"...","command":"..."}] } and screen every independently executable member.
  2. Exit 2 and decision=BLOCK means the matching candidate was not eligible for submission. Preserve its SHA-256 and source in the preflight evidence, change the representation, and screen the changed exact action once.
  3. Exit 0 means only that the currently registered mechanical families did not block the input. Continue all workflow, authority, scope, semantic, and evidence gates.
  4. Exit 1 or decision=ERROR means the preflight route itself failed. Preserve it and use a constrained representation or block only the dependent PowerShell member.

The known foreach family is the parser-invalid form foreach (...) { ... } | Command. Use an intermediate array or ForEach-Object when semantics are preserved. Strings, comments, here-strings, subexpressions, and a later separate pipeline must not be falsely classified as this family.

The literal-dollar family applies when a command argument must contain a literal $skill-name or similar token. Use a non-expanding literal transport or exact post-generation patch, then read back the consumer file. Do not infer the caller's intention from a dollar sign alone; the input JSON must mark literal_dollar_required=true for this constraint to apply.

Read constraint-contract.md when adding a confirmed mechanical family. A new family requires an exact recurrence discriminator, safe counterexamples, member-level applicability, bounded proof ceiling, and master lineage.

Files

What ships with it

2 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. 1mo ago Changed · +23 tokens per session 0f81177f957c
  2. 1mo ago First seen · 20 lines · 56 tokens per session scan A 147a9cf5a320

Subscribe to this mod's changes

powershell-exact-action is a skill published in the GitHub repository Chisiki1/objective-integrity-framework (23 stars, last pushed 8d ago), licensed Apache-2.0. It adds 79 tokens to every session and 483 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-08.

Related

Other skills, from other repositories