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 kingcharleslzy-ai/claude-code-deepseek-3p-parity-skill --skill claude-3p-paritygit clone --depth 1 https://github.com/kingcharleslzy-ai/claude-code-deepseek-3p-parity-skillWrote 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/kingcharleslzy-ai/claude-code-deepseek-3p-parity-skill/claude-3p-parity)<a href="https://agentmods.dev/skills/kingcharleslzy-ai/claude-code-deepseek-3p-parity-skill/claude-3p-parity"><img src="https://agentmods.dev/badge/skills/kingcharleslzy-ai/claude-code-deepseek-3p-parity-skill/claude-3p-parity/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/kingcharleslzy-ai/claude-code-deepseek-3p-parity-skill/claude-3p-parity"><img src="https://agentmods.dev/badge/skills/kingcharleslzy-ai/claude-code-deepseek-3p-parity-skill/claude-3p-parity.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 | $0.00122 | $0.02692 |
| Opus 5 | $0.00061 | $0.01346 |
| Sonnet 5 | $0.00024 | $0.00538 |
| Haiku 4.5 | $0.00012 | $0.00269 |
Grade B, and why
claude-3p-parity scanned grade B with 1 finding 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 12d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `~/.claude/settings.json`: bypass permission defaults, protected-path prompt skip, common tool allowlist, additional directories, sandbox knobs, DeepSeek V4 Pro/Flash model environment (with `[1m]` context suffix), sub How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude 3p Parity
Core Rule
Treat parity as best-effort. Do not claim third-party inference can become identical to first-party Claude. Auto mode, macOS privacy prompts, provider-side model support, and missing /v1/models discovery cannot always be fixed by local settings.
Always inspect first. A "one-click repair" still means: run dry-run, read the current state and missing items, summarize the planned changes for the user, then apply only after the user has explicitly approved the write step. The only exception is when the user has already said in the same turn to apply without another confirmation.
Workflow
-
Run the bundled script in dry-run mode first:
python3 ~/.claude/skills/claude-3p-parity/scripts/claude_3p_parity.py -
Review the report's
inspection,connectivity, andchangessections. Tell the user:- what the current Claude/3p/MCP/runtime state is;
- which expected permissions, env vars, MCP servers, model mappings, runtime pieces, or network paths are missing;
- exactly which files or external settings the apply step will change;
- whether live network probing was skipped or approved. By default, the script only inspects proxy/npm/git config to avoid permission popups.
- whether secret-looking values are present in config files. Do not print the values; tell the user which file contains them and whether the location is expected.
-
Only run live network probes when the user approves possible outbound-network permission prompts:
python3 ~/.claude/skills/claude-3p-parity/scripts/claude_3p_parity.py --network-check -
If npm/GitHub/Hugging Face/Claude release downloads are blocked or slow in mainland China, prefer this order:
- use an existing user proxy if one is already configured;
- ask before injecting a proxy into Claude/MCP env with
--proxy-url; - ask before changing global npm config with
--set-npm-registry https://registry.npmmirror.com; - keep
HF_ENDPOINT=https://hf-mirror.comfor memory/embedding tools; - use
NO_PROXYfor localhost/private-network routes when a proxy is supplied; - use
NODE_EXTRA_CA_CERTSorCLAUDE_CODE_CERT_STORE=systemfor corporate TLS inspection, not TLS verification disablement; - do not run runtime overlay until
https://downloads.claude.ai/is reachable through direct network or proxy.
What ships with it
3 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.
- 12d ago First seen · 181 lines · 122 tokens per session scan B 58af8c6bb05c
claude-3p-parity is a skill published in the GitHub repository kingcharleslzy-ai/claude-code-deepseek-3p-parity-skill (5 stars, last pushed 4mo ago), licensed MIT. It adds 122 tokens to every session and 2,692 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
cherry-assistant-guide
A guide for looking up Cherry Studio's product details and diagnosing problems such as connection failures, setup errors, and runtime issues.
cherry-electron-dev
Develop, fix, and profile Cherry Studio in a tracked Electron instance. Use for everyday implementation, UI and interaction work, bug fixing, runtime debugging, DevTools inspection, lag or jank investigation, CPU and memory monitoring, leak checks, and startup-performance analysis; reuse a verified workspace instance…
cherry-studio-feedback
A guide for handling Cherry Studio bug reports, interface problems, user-experience issues, and feature suggestions.
deliver-edge-cases
Documents edge cases, error states, boundary conditions, race conditions, and recovery paths for a feature - the systematic catalog of what can go wrong and the failure modes to design for. Use during specification to map the failure surface and ensure comprehensive coverage, or during QA planning to identify boundary…
utility-pm-skill-auditor
Run a repo-wide cross-cutting governance audit via the pm-skill-auditor sub-agent. Aggregates the enforcing validator suite, re-derives aggregate counters, and surfaces cross-cutting issues no single validator catches, graded P0/P1/P2/P3 with a machine-readable status. Use for pre-release readiness checks or a…
fastgpt-docker-deploy
FastGPT Docker Compose self-hosting deployment workflow. Use when a user asks an AI agent to deploy FastGPT with Docker by referencing /deploy/SKILL.md, including creating an empty fastgpt directory, running the install script in non-interactive mode, starting Docker Compose, monitoring service health, troubleshooting…