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/jimmypaolini/codebase/conformetry-validatenpx skills add JimmyPaolini/codebase --skill conformetry-validategit clone --depth 1 https://github.com/JimmyPaolini/codebaseWhat 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 | $0.00097 | $0.01755 |
| Opus 5 | $0.00048 | $0.00877 |
| Sonnet 5 | $0.00019 | $0.00351 |
| Haiku 4.5 | $0.00010 | $0.00176 |
Grade A, and why
conformetry-validate 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.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Checking conformance and fixing differences
Conformance measures an instance — generated code on disk — against the template it came from. A difference is something the template declares that the instance lacks.
The one rule that governs every language
The instance must carry everything its template declares. Anything it adds is never a difference.
Extra declarations, extra keys, extra lines, extra files, reordered class members: all fine. So the fix for a difference is almost always to add what is missing, never to delete what is extra. An agent that starts removing content to make a file conform is working against the mechanism.
Implement freely inside generated files. Function bodies are not compared at all.
Running it
Per project, or across the workspace:
nx run <project>:conformetry-validate
nx run-many --targets=conformetry-validate
Without Nx, the command-line host does the same:
conformetry validate
Both accept a language filter, and the command-line host also accepts a one-off glob override in place of the configured instances. Narrowing is for iterating; let the full run be the gate.
Reading a report
A report opens with a score summary when anything scored below a perfect match, then lists each file, the instance and template it compared, and every difference with a suggested fix:
1. file: orders.service.ts
Instance: packages/widgets/src/modules/orders/orders.service.ts
Template: configuration/conformetry-templates/nestjs-service-module/…
1. Missing Decorator "Injectable"
Instance: Line 12, Column 1
Template: Line 8, Column 1
Fix : Add the missing Decorator "Injectable" to the instance file.
Read the Fix line before inventing a remedy. Every difference carries one,
and it names the specific construct rather than describing the file in general.
Locations are 1-based. JSON differences report a path such as scripts.build[0]
instead of a line, because a key has no meaningful line in a reformatted file.
What ships with it
2 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.
- yesterday First seen · 189 lines · 97 tokens per session scan A 346db03a8e51
conformetry-validate is a skill published in the GitHub repository JimmyPaolini/codebase (0 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 1,755 once invoked, about $0.0005 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 2026-09-01.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.