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 instructions/adityaarsharma/pickle/claude-mdgit clone --depth 1 https://github.com/adityaarsharma/pickleWrote 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/instructions/adityaarsharma/pickle/claude-md)<a href="https://agentmods.dev/instructions/adityaarsharma/pickle/claude-md"><img src="https://agentmods.dev/badge/instructions/adityaarsharma/pickle/claude-md.svg" alt="Measured on agentmods" 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 | $0.01051 | $0.01051 |
| Opus 5 | $0.00526 | $0.00526 |
| Sonnet 5 | $0.00210 | $0.00210 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade B, and why
pickle CLAUDE.md scanned grade B with 2 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 4d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
2. Atomic writes for any file containing a token: tempfile + fsync + `os.replace`, then `chmod 600`. Never truncate-in-place — a crash would wipe the user's other MCP servers. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
sleep 2; curl -fs http://127.0.0.1:8788/health && echo OK; kill %1 How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Pickle contributor rules
Rules for any agent (Claude or otherwise) editing this repo. Read before changing anything.
1. Pickle is ONE product, and it is FREE + LOCAL
Pickle is a single free, open-source (MIT) tool built by Aditya Sharma. It's an MCP server you run on your own machine. There is no paid tier, no hosted server, no account, no key issuance, no telemetry.
- ✅ "Free, open source, runs on your machine, no account, no telemetry" — all true, keep it accurate.
- ❌ Never reintroduce a Pro tier, a hosted signup, a
pickle_free_key, Brevo/email capture, an admin panel, or usage tracking intoserver-remote/. Those were removed on purpose. - ❌ Never write "free forever" (say "free · no paid tier") or "your data never leaves your machine" (false — Pickle reads ClickUp/Slack/Teams; say "no middleman — only your tools, with your token").
2. Privacy claims must be literally true
The honest, verifiable claim: Pickle runs locally and talks only to the platform APIs (ClickUp / Slack / Microsoft Graph) using the user's own token, which lives in their local MCP config. Nothing is sent to any Pickle server — there is no Pickle server.
- ✅ Allowed: "no account", "no telemetry", "no phone-home", "no middleman", "your token stays in your local config", "read the code to verify".
- ❌ Banned: "your data never leaves your machine" (it goes to the tools you audit — that's the job).
If you add a network call to anything other than the user's own platform APIs, that's a bug — remove it.
3. The only token is the user's OWN platform token
Pickle issues nothing. The user supplies their own CLICKUP_API_KEY (pk_…), SLACK_TOKEN (xoxp-…), or TEAMS_TOKEN (Graph). These live in the local MCP config env block and are used to call the platform on the user's behalf. Never persist, log, or echo them.
4. Token handling in shell (installer + skills)
- Never echo a token. Read with
read -rs. Pass to helpers via env, never argv (keeps it out of the process list + shell history). - Atomic writes for any file containing a token: tempfile + fsync +
os.replace, thenchmod 600. Never truncate-in-place — a crash would wipe the user's other MCP servers. - Build JSON with
python3/jq, never string-interpolate a name/title/token into-d "{...}"(a display name can contain",$, backticks — that's RCE).
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.
- 4d ago First seen · 60 lines · 1,051 tokens per session scan B a00d6aead663
pickle CLAUDE.md is an instructions file published in the GitHub repository adityaarsharma/pickle (3 stars, last pushed 20d ago), licensed MIT. It adds 1,051 tokens to every session, about $0.0053 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
teams-mcp copilot-instructions.md
Instructions for floriscornel/teams-mcp, covering copilot instructions — teams-mcp, project overview, architecture, commands and ci/cd.
clickup-mcp-server CLAUDE.md
Claude Code instructions for Chisanan232/clickup-mcp-server, covering claude.md — clickup mcp server, project overview, repository structure, development setup and install pre-commit hooks.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).