update

update is a skill for Claude Code from ChainGPT-org/chaingpt-claude-skill. It costs 38 tokens per session (1,292 once invoked), scanned A, original, MIT.

An update manager for the ChainGPT skill, which provides tools or instructions for working with ChainGPT.

In plain words
What is it for?
Read the current version, fetch updates, display a categorized changelog, and apply approved updates.
Why use it?
It shows whether the installed skill is outdated and describes available changes before applying them.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions Claude Code.

Part of the chaingpt plugin — 24 skills, 1 command, 3 agents, 1 hook, 1 MCP server shipped together

Good fit Read the current version, fetch updates, display a categorized changelog, and apply approved updates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chaingpt-org/chaingpt-claude-skill/update
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 ChainGPT-org/chaingpt-claude-skill --skill update
Clone the repo
git clone --depth 1 https://github.com/ChainGPT-org/chaingpt-claude-skill

Made for: Claude Code.

Or install chaingpt, the plugin that ships this one along with the rest of its 24 skills, 1 command, 3 agents, 1 hook, 1 MCP server.

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 update

README.md
[![agentmods](https://agentmods.dev/badge/skills/chaingpt-org/chaingpt-claude-skill/update/github.svg)](https://agentmods.dev/skills/chaingpt-org/chaingpt-claude-skill/update)
Your own site
<a href="https://agentmods.dev/skills/chaingpt-org/chaingpt-claude-skill/update"><img src="https://agentmods.dev/badge/skills/chaingpt-org/chaingpt-claude-skill/update/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 update

Your own site · 80×15
<a href="https://agentmods.dev/skills/chaingpt-org/chaingpt-claude-skill/update"><img src="https://agentmods.dev/badge/skills/chaingpt-org/chaingpt-claude-skill/update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,292 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Rogue Agent · line 3
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
How audits are shown
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 $0.00038 $0.01292
Opus 5.5 $0.00015 $0.00517
Sonnet 5.5 $0.00008 $0.00258
Haiku 4.5 $0.00004 $0.00129

Measured 1mo ago against content hash f8f97a5bebc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

update 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.

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.

skills/update/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ChainGPT Skill Update Manager

When the user invokes this skill, follow these steps in order:

Step 1: Check the Prepared Local Checkout

Use the prepared local checkout described in the root README. Do not update a marketplace cache or replace files in a running plugin session. Have the user stop that session before applying changes, or prepare a separate checkout for the next session.

From the checkout root, read the installed version and check for local changes:

cat VERSION
git status --short

Report the current version. If there are local changes, stop the update and let the user preserve them; do not stash, reset, overwrite, or merge them automatically.

Step 2: Check for Updates

Verify that origin is the intended ChainGPT repository. Fetch updates without applying them, then record the full commit SHA from the fetched origin/main:

git -c core.hooksPath=/dev/null fetch origin main
CHAINGPT_REVIEWED_COMMIT="$(git rev-parse --verify origin/main)"
printf '%s\n' "$CHAINGPT_REVIEWED_COMMIT"
git log --oneline "HEAD..$CHAINGPT_REVIEWED_COMMIT"
git diff --stat HEAD "$CHAINGPT_REVIEWED_COMMIT"

Retain that exact SHA throughout review and application. If a later command runs in a fresh shell, set CHAINGPT_REVIEWED_COMMIT to the recorded literal SHA, never to a freshly resolved remote ref.

  • If HEAD equals the recorded SHA, report that no update is available.
  • If the histories diverge or the local checkout is ahead, stop and report the difference. Do not reset or create a merge commit.
  • Otherwise, proceed to review the fetched commit before changing the checkout or installing dependencies.

Step 3: Review the Exact Update

Inspect the full diff against the recorded SHA. Pay particular attention to dependency manifests and lockfiles, mcp-server/dist/, the launcher, hooks, .mcp.json, plugin metadata, scripts and skills:

git diff HEAD "$CHAINGPT_REVIEWED_COMMIT"

Check the candidate revision's security and build results. Do not execute downloaded hooks, build scripts or dependency lifecycle scripts during review. Explain material changes and unresolved findings before asking to apply the exact recorded SHA. Categorize changes where useful:

Read the full file on GitHub · 108 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. 1mo ago Changed · +18 lines f8f97a5bebc9
  2. 1mo ago First seen · 90 lines · 38 tokens per session scan A 1b9f0a5a18f5

Subscribe to this mod's changes

update is a skill published in the GitHub repository ChainGPT-org/chaingpt-claude-skill (7 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,292 once invoked, about $0.0002 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 2026-08-30.