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/paultyng/testagent/update-compatibilitynpx skills add paultyng/testagent --skill update-compatibilitygit clone --depth 1 https://github.com/paultyng/testagentWhat 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 | $0.00122 | $0.01597 |
| Opus 5 | $0.00061 | $0.00798 |
| Sonnet 5 | $0.00024 | $0.00319 |
| Haiku 4.5 | $0.00012 | $0.00160 |
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 3d 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 — 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:claudeanddumpcli:codexexist;dumpcli:cursorlands 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.mdfor the authoritative source URLs and local probing recipes. - Run the local probes (subcommand
--helpdumps,dumpcli:<vendor>tasks). - Fetch each documented page in
sources.md. Tolerate one retry per JS-rendered page; markTODO: sourceon a stubborn fetch and continue rather than guess. - Cross-reference against the current
## <Vendor>section inCOMPATIBILITY.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.mdas the skeleton. Keep the other vendors' sections inCOMPATIBILITY.mduntouched. - Run
task dumpcli:<vendor>(where available) to regenerate the contract artifact; commit both COMPATIBILITY.md and the regeneratedcompat/<vendor>.cli.txt.
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.
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.
- 3d ago First seen · 103 lines · 122 tokens per session scan A 3e4aa9fa5f9c
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 $0.0006 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
mermaid-visualizer
Transform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention.
apm-usage
Activate when the user asks about APM (Agent Package Manager): installing, configuring, authoring, or troubleshooting AI-agent packages, dependencies, compilation, MCP servers, policy, or any apm CLI command.
clean-user-facing-text
Audit and finalize authorized natural-language text meant for readers: strip suspicious invisible Unicode, then rewrite prose while keeping facts, meaning, and the writer's voice. Use when the user asks to clean, humanize, polish, or finalize articles, manuscripts, reports, documentation, emails, product copy, UI…
sessions
Search and ask questions about coding agent session history across Claude Code, Codex, and Cursor. Use when asking what was worked on, what was tried before, how a problem was investigated across sessions, what happened recently, or any question about past agent sessions. Also use when the user references prior…
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
map-review
Interactive 4-section code review using monitor, predictor, and evaluator agents plus the user and maintainer role reviewers on current changes. Use when reviewing a diff, PR, or staged work before merge. Do NOT use to plan or implement; use map-plan or map-efficient.