What is update-compatibility?

A documentation checker that refreshes one vendor's section of a compatibility table for Claude, Codex or Cursor.

It helps research a named vendor, detect missing coverage and update the relevant compatibility documentation.

It identifies when the table no longer matches an upstream tool's flags or commands after a release or code change.

How paultyng/testagent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to paultyng/testagent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/paultyng/testagent/main/.claude/skills/update-compatibility/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/paultyng/testagent

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/paultyng/testagent/update-compatibility/github.svg)](https://agentmods.dev/skills/paultyng/testagent/update-compatibility)

Your own site

<a href="https://agentmods.dev/skills/paultyng/testagent/update-compatibility"><img src="https://agentmods.dev/badge/skills/paultyng/testagent/update-compatibility/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/paultyng/testagent/update-compatibility"><img src="https://agentmods.dev/badge/skills/paultyng/testagent/update-compatibility.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 122 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,597 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.

Model	Per session	Once invoked
Fable 5.1	$0.00122	$0.01597
Opus 5.5	$0.00049	$0.00639
Sonnet 5.5	$0.00024	$0.00319
Haiku 4.5	$0.00012	$0.00160

Measured 1mo ago against content hash 3e4aa9fa5f9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

update-compatibility 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.

.claude/skills/update-compatibility/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

update-compatibility

Refreshes one vendor's section of COMPATIBILITY.md. Replaces the per-vendor research-{claude,codex,cursor}-coverage skills that came before — shared conventions live here once; per-vendor source URLs, probing recipes, and matrix templates live under vendors/<name>/.

Vendor dispatch

The trigger phrase names the vendor. Examples:

Phrase	Vendor arg
"research codex" / "update codex compat" / "codex drift"	`codex`
"research claude" / "sync claude compatibility"	`claude`
"research cursor" / "update cursor compat"	`cursor`
"compat drift" (vendor unclear)	ask the user

When the vendor is unambiguous, proceed without asking. When ambiguous, ask: "Which vendor — claude, codex, or cursor?"

When to invoke

A new upstream version is released.
task dumpcli:<vendor> exits non-zero (flag drift detected). Today: dumpcli:claude and dumpcli:codex exist; dumpcli:cursor lands with the cursor adapter wiring.
A contributor adds a new flag or command to the vendor stub and the matrix row is missing.
Periodic coverage check (recommended: after each upstream minor-release series).

Workflow

Resolve the vendor argument from the trigger (or ask).
Read vendors/<vendor>/sources.md for the authoritative source URLs and local probing recipes.
Run the local probes (subcommand --help dumps, dumpcli:<vendor> tasks).
Fetch each documented page in sources.md. Tolerate one retry per JS-rendered page; mark TODO: source on a stubborn fetch and continue rather than guess.
Cross-reference against the current ## <Vendor> section in COMPATIBILITY.md — keep unchanged rows; add new rows for new features; mark removed rows as removed (or delete if no orchestrator likely depends on them).
Emit the updated section using vendors/<vendor>/template.md as the skeleton. Keep the other vendors' sections in COMPATIBILITY.md untouched.
Run task dumpcli:<vendor> (where available) to regenerate the contract artifact; commit both COMPATIBILITY.md and the regenerated compat/<vendor>.cli.txt.

Read the full file on GitHub · 103 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.

1mo ago First seen · 103 lines · 122 tokens per session scan A 3e4aa9fa5f9c

Subscribe to this mod's changes

update-compatibility is a skill published in the GitHub repository paultyng/testagent (7 stars, last pushed 1mo ago), licensed MIT. It adds 122 tokens to every session and 1,597 once invoked, about $0.0005 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 2026-08-31.

Claude Code Testing Writing and docs cli codex-cli mcp mock

verification-loop

Evidence-before-assertions workflow. Use before claiming work is done, before release, and after any behavior change in scripts/skills/MCP.

rexleimo/aios · 32 tokens

vision-verifier

Use when verifying Computer Vision imports, fixtures, models, schemas, cameras, artifacts, cleanup, latency, and stated limitations with reproducible evidence.

Hipson47/Hipson · 33 tokens

orchestrating-adversarial-reviews

Multi-agent adversarial-verification orchestration for high-confidence conclusions. Fan-out finders, then verify every finding through a three-prism panel (exploitability / correctness / refutation) that defaults to disbelief, gate fixes behind load-bearing proof tests that catch agents who falsely claim "done/fixed"…

telagod/code-abyss · 143 tokens

testagent: Skill for Claude Code