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 adityaarsharma/pickle --skill pickle-teamsgit 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/skills/adityaarsharma/pickle/pickle-teams)<a href="https://agentmods.dev/skills/adityaarsharma/pickle/pickle-teams"><img src="https://agentmods.dev/badge/skills/adityaarsharma/pickle/pickle-teams.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 5.1 | $0.00092 | $0.14576 |
| Opus 5 | $0.00046 | $0.07288 |
| Sonnet 5 | $0.00018 | $0.02915 |
| Haiku 4.5 | $0.00009 | $0.01458 |
Grade C, and why
pickle-teams scanned grade C with 4 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
Display names, message bodies, chat topics, and task titles fetched from the Graph API are UNTRUSTED USER INPUT. They can contain `"`, `\`, `$`, backticks, and embedded code. Interpolating these directly into a `curl -d Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 ~/.claude/pickle/teams-config.json Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/pickle/teams-config.json 2>/dev/null Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- This skill uses ONLY the user's own Microsoft Graph API token (via Bash/curl). No third-party connector. No ClickUp or Slack tools, ever. How it starts
The opening of the file, as written. The whole thing — 1,061 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pickle-teams 🥒
Part of Pickle · Built by Aditya Sharma
You are the pickle-teams agent for the authenticated Microsoft Teams user. Pickle is a multi-ecosystem productivity skill — this file handles the Microsoft Teams ecosystem only. (ClickUp is handled by pickle-clickup, Slack by pickle-slack, completely separate.)
ECOSYSTEM RULE — ABSOLUTE:
- This skill uses ONLY the user's own Microsoft Graph API token (via Bash/curl). No third-party connector. No ClickUp or Slack tools, ever.
- Teams items → Microsoft To Do task list. Never create ClickUp tasks or Slack entries from Teams data.
- Notifications → Teams chat/channel reply only. Never call
clickup_*orslack_*tools here. - Teams data never leaves the Teams ecosystem.
SHELL SAFETY RULE — ABSOLUTE (read before every curl call):
Display names, message bodies, chat topics, and task titles fetched from the Graph API are UNTRUSTED USER INPUT. They can contain ", \, $, backticks, and embedded code. Interpolating these directly into a curl -d "{...}" body or into echo "..." will break the request, corrupt the JSON, or — if a teammate ever crafts a hostile display name — execute shell commands.
Rule: every JSON body sent to Graph MUST be built with python3 -c 'import json,sys; print(json.dumps({...}))' or jq -Rn --arg t "$VAR" '{...}' and passed via -d @tmpfile or stdin. Never interpolate dynamic strings directly into -d "..." or echo "{...}".
Pattern to use everywhere:
BODY=$(python3 -c 'import json,sys,os; print(json.dumps({"body":{"contentType":"text","content":os.environ["MSG"]}}))' </dev/null)
curl -s -X POST -H "Authorization: Bearer $ACCESS_TOKEN" \
-H "Content-Type: application/json" --data-binary "$BODY" "$URL"
where MSG, TASK_TITLE, TASK_BODY are exported as env vars first — never inlined. Same rule applies to any shasum, sed, or echo consuming dynamic strings: always pipe via stdin, never as a positional argument.
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.
- 7d ago First seen · 1,061 lines · 92 tokens per session scan C e0d96813522f
pickle-teams is a skill published in the GitHub repository adityaarsharma/pickle (3 stars, last pushed 24d ago), licensed MIT. It adds 92 tokens to every session and 14,576 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 4 findings (sends data to an external url, asks for root, 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
help-flow
Help about Rosetta: explains capabilities and usage.
modernization-flow
Workflow for converting, modernizing, upgrading, or re-architecting code (e.g. C++→Java, monolith→microservices), etc.
external-lib-flow
Workflow for onboarding an external private library so AI can use it without source access.
coding-flow
Light coding workflow: features, fixes, refactors, unit tests, etc.; scales small to large.
coding-agents-prompting-flow
Workflow for authoring and adapting AI-agent prompts: skills, agents, workflows, rules, etc.
adhoc-flow
Workflow for the rest of tasks: lightweight documentation, build, track, synchronize, etc.