agent-integrity

A workspace check for whether a Codex agent’s approved setup has changed, with options to record or sign its configuration summary.

In plain words
What is it for?
Use it to verify the current agent setup, capture a snapshot, approve a new baseline, or generate signed manifest and session records.
Why use it?
It helps detect configuration drift and create records of the agent baseline without exposing secrets or raw configuration values.

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/agentrust-io/integrations/agent-integrity
Any agent
npx skills add agentrust-io/integrations --skill agent-integrity
Clone the repo
git clone --depth 1 https://github.com/agentrust-io/integrations

Made for: Claude Code, Codex.

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 712 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 $0.00033 $0.00712
Opus 5 $0.00016 $0.00356
Sonnet 5 $0.00007 $0.00142
Haiku 4.5 $0.00003 $0.00071

Measured yesterday against content hash dfab9b4b51b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-integrity 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 yesterday.

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.

plugins/agentrust-codex/skills/agent-integrity/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgenTrust agent integrity

Use the capture engine shipped with this plugin. Resolve ../../engine/capture.py from this SKILL.md to an absolute path before running it. Resolve ../../scripts/signing-python.py the same way.

The engine stores only names and hashes. Do not inspect auth.json, transcript files, tool inputs, tool outputs, environment secrets, or raw configuration values for this workflow.

Select the operation

  • Verify is the default. Run it when the user asks whether the Codex agent changed, requests an integrity check, or names no operation.
  • Snapshot shows the current fingerprints without comparing or changing the baseline.
  • Approve replaces the baseline. Run it only when the user asked to establish, accept, approve, or rebaseline the current composition. A verification result alone does not authorize approval.
  • Report creates signed Agent Manifest and TRACE records. The report does not alter the approved baseline.

Use the current working directory as the workspace unless the user names another one. The engine scopes baselines by a hash of the Git root, so checks in different repositories do not overwrite each other.

Run the engine

Use python3 on macOS or Linux and py -3 on Windows.

Verify:

python3 <engine-path> verify --cwd <workspace>

Snapshot:

python3 <engine-path> snapshot --cwd <workspace>

Approve after explicit user authorization:

python3 <engine-path> approve --cwd <workspace>

For a signed report, run the signing environment bootstrap with Python 3.11 or newer. It creates a venv under $CODEX_HOME/agentrust/signing-venv and installs the exact released versions from this plugin's requirements.txt. This is the only step in the workflow that accesses PyPI.

python3 <signing-bootstrap-path>
<printed-python-path> <engine-path> report --cwd <workspace> --out <output-directory>

If the SessionStart hook did not capture the active model, add --model <active-model-slug> only when the model slug is present in the current Codex session. Never guess it.

Read the full file on GitHub · 89 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. yesterday First seen · 89 lines · 33 tokens per session scan A dfab9b4b51b6

Subscribe to this mod's changes

agent-integrity is a skill published in the GitHub repository agentrust-io/integrations (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 33 tokens to every session and 712 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 2026-08-31.

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

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

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens