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 skills add uwuclxdy/agenticat --skill parity-gapgit clone --depth 1 https://github.com/uwuclxdy/agenticatWrote 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/uwuclxdy/agenticat/parity-gap)<a href="https://agentmods.dev/skills/uwuclxdy/agenticat/parity-gap"><img src="https://agentmods.dev/badge/skills/uwuclxdy/agenticat/parity-gap/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.
<a href="https://agentmods.dev/skills/uwuclxdy/agenticat/parity-gap"><img src="https://agentmods.dev/badge/skills/uwuclxdy/agenticat/parity-gap.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00024 | $0.01172 |
| Opus 5 | $0.00012 | $0.00586 |
| Sonnet 5 | $0.00005 | $0.00234 |
| Haiku 4.5 | $0.00002 | $0.00117 |
Grade A, and why
parity-gap 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parity Gap
Bring this program (default: cwd) up to (and past) a reference. Map both sides, diff them, confirm scope in rounds of 4 questions before writing anything, then author tasks into docs/todo.md, via the todo skill if installed or directly otherwise.
1. Resolve the Inputs First
this programdefaults to the working directory. Name another explicitly to override.referenceis one of:- a remote repository: clone it into a temp dir then treat as local codebase.
- a local codebase (path on disk): read its tree, entrypoints, commands, modules.
- a docs/spec/feature list (file or pasted text): treat every command, endpoint, flag, or behavior it describes as a reference feature.
- If either is ambiguous (which repo? which spec?) or the reference can't be reached once identified (private, no network, no read access), ask anything and no guesses before mapping.
2. Map Each Side (Inline, Single-Pass)
Map what each side exposes to an end user; skip internals and file structure. The user-reachable surface:
- commands / subcommands / flags
- exported APIs, routes, endpoints
- config keys, env vars
- UI/TUI/CLI surfaces and the actions they expose
- notable behaviors, formats, integrations
Use Grep/Read/semantic code search inline. The reference is the spec side, so read it thoroughly; the program is the have side. If the reference is too big to hold inline, offload its mapping to a read-only exploration subagent (e.g. Explore) and diff from the returned inventory.
3. Diff into Two Buckets
- Parity gaps: capabilities the reference has that this program lacks. The core of the output.
- Improvements: things beyond the reference (better defaults, affordances the reference itself lacks, wins spotted during mapping). List these in their own section; never mix them into the parity list.
Drop anything the program already has. Note cascade order where one gap blocks others.
4. Confirm Scope
Before writing a single task, run clarifying questions through AskUserQuestion (max 4 per round, batched rather than trickled), looping rounds until scope is nailed. (On other harnesses, check for a native equivalent first: opencode's question tool, gemini-cli's ask_user tool, or codex's request_user_input [Plan Mode only]. Fall back to a plain numbered message and wait for answers only if none is available.) This gate is the point of the skill: the user reviews the gap list as questions, not as a finished file.
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 Changed 16d0b596a1d4
- 9d ago First seen · 78 lines · 24 tokens per session scan A 00a6d78bde44
parity-gap is a skill published in the GitHub repository uwuclxdy/agenticat (5 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 1,172 once invoked, about $0.0001 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
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
adk-debug
Diagnoses misbehaving ADK agents by inspecting sessions, events, tool calls, and the exact request that reached the model. Covers the adk run CLI and the adk web dev server with its session, trace, and debug HTTP endpoints. Use when an agent returns the wrong answer, ignores a tool or swallows a tool error, hangs…
typescript-testing
Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, or validating TypeScript package changes. Do not use for Python-only checks.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
potpie-cli
Use when the task is centered on running, explaining, configuring, or troubleshooting the potpie command: doctor, login, pot management, source registration, search, graph workbench reads/writes, and pot scope behavior.
rubber-duck
Adversarial "rubber duck" review that turns explaining-out-loud into a hallucination check. The main session is the PRESENTER (it did the work — a design doc, investigation, or analysis — and holds the real reasoning) and reconstructs the topic to a LISTENER — a spawned subagent pinned to a DIFFERENT-vendor model that…