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.
npx agentmods add skills/cboone/agent-harness-plugins/check-versionsnpx skills add cboone/agent-harness-plugins --skill check-versionsgit clone --depth 1 https://github.com/cboone/agent-harness-pluginsWrote 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.
[](https://agentmods.dev/skills/cboone/agent-harness-plugins/check-versions)<a href="https://agentmods.dev/skills/cboone/agent-harness-plugins/check-versions"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/check-versions.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00065 | $0.01023 |
| Opus 5 | $0.00032 | $0.00511 |
| Sonnet 5 | $0.00013 | $0.00205 |
| Haiku 4.5 | $0.00006 | $0.00102 |
Grade A, and why
check-versions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check Versions
Verify that plugin versions and marketplace.json are correct and consistent after changes on the current branch.
Workflow
1. Determine the Comparison Base
Detect the default branch:
gh repo view --json defaultBranchRef --jq '.defaultBranchRef.name'
Fall back to local detection if gh is unavailable:
git rev-parse --abbrev-ref origin/HEAD | sed 's@^origin/@@'
Find the merge base between the default branch and HEAD:
git merge-base < default-branch > HEAD
If HEAD equals the merge base (on the default branch or no divergent commits), compare against the state before the most recent merge instead — use the most recent merge commit's first parent as the comparison base:
git rev-parse "$(git log --merges -1 --format='%H' HEAD)^1"
2. Identify Changed Plugins
List files changed since the comparison base and group them by plugin directory:
git diff --name-only < base > ..HEAD
A file belongs to plugin foo if its path starts with plugins/foo/. For each plugin, track:
- Content changes: files other than
.claude-plugin/plugin.jsonthat were modified, added, or deleted - Version file changed: whether
.claude-plugin/plugin.jsonitself was modified
Also detect new plugins (directories at HEAD that did not exist at the base) and removed plugins (directories at the base that no longer exist).
3. Check Plugin Version Bumps
For each plugin with content changes:
- Read the current version from
plugins/<name>/.claude-plugin/plugin.json - Read the base version:
git show <base>:plugins/<name>/.claude-plugin/plugin.json - Compare:
- New plugin (file absent at base) — version should be
1.0.0 - Content files changed but version unchanged — flag as missing version bump
- Version changed — verify the bump direction is forward, not a regression
- New plugin (file absent at base) — version should be
Assess bump level (informational):
- Wording-only or prompt changes → patch
- New files, new capabilities → minor
- Deleted or restructured skill/hook files → major
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.
- 4d ago First seen · 118 lines · 65 tokens per session scan A 8c8b669fd9e2
check-versions is a skill published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 1,023 once invoked, about $0.0003 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.
Other skills, from other repositories
feature-spec
Creates a complete product feature specification with acceptance criteria, scope, dependencies, and risks. Delegates to the Prometeo (PM) agent.
implement-feature
Implements a feature from its specification. Reads the spec, designs architecture, writes code and tests. Delegates to the Forja (Dev) agent.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).
02-user-stories
Produces or refines ordered User Stories from an Epic, Product Brief, PRD, or bounded request. Use when the user wants to slice, write, assess, order, or persist Stories. Not for Epics or implementation.
10-learn
Capture durable project learnings. Use when the user wants to remember, record, or formalize a decision, convention, lesson, pitfall, reusable workflow, or review finding. Not for preferences or temporary notes.
11-browser-qa
Run post-review browser QA and produce short named videos for a locked happy path and sourced browser edge cases. Use when the user wants concise reviewer evidence for a web journey. Not for API, CLI, automated tests, diff review, or application fixes.