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 wecode-ai/Wegent --skill conversationsgit clone --depth 1 https://github.com/wecode-ai/WegentWrote 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/wecode-ai/wegent/conversations)<a href="https://agentmods.dev/skills/wecode-ai/wegent/conversations"><img src="https://agentmods.dev/badge/skills/wecode-ai/wegent/conversations/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/wecode-ai/wegent/conversations"><img src="https://agentmods.dev/badge/skills/wecode-ai/wegent/conversations.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 | $0.00023 | $0.00445 |
| Opus 5.5 | $0.00009 | $0.00178 |
| Sonnet 5.5 | $0.00005 | $0.00089 |
| Haiku 4.5 | $0.00002 | $0.00044 |
Grade A, and why
conversations 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 2d 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.
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.
What it actually says
Wework control routing:
- Use wework_control for Wework conversation discovery, native history, cross-conversation continuation, confirmed PR bindings and personal schedules. Discovery and history queries cover this device, cloud history and other owned devices by default. Native conversation continuation supports other owned devices through the desktop's existing send API and device policy.
- Use get_conversation_creation_options before choosing creation settings. create_conversation accepts composer options and an explicit target device/model; remote creation uses existing Backend device policy. Use the native conversation_id returned by discovery for remote continuation; cloud-history references without a Runtime address are read-only.
- Read get_current_context and discover capabilities when needed. Continue the exact conversation_id returned by the tools. Use a stable request_key per user instruction or CI failure (repository, PR, head SHA, run ID and attempt). Check get_operation after delivery; accepted is not completed.
- For weekly reports, list conversations with updated_after set to the period start, include archived conversations, follow every next_cursor and every history cursor, and select messages by their timestamps. Do not use updated_before to exclude conversations with newer activity. State any missing coverage.
- When a user names a device, resolve its device_id from creation options and query that device directly. Use list_conversations/search_conversations to inspect existing conversations; do not create a new conversation just to discover them. query_timeout in coverage identifies a source to retry with device_id.
- Inspect coverage.unavailable_reasons in conversation search and listings. Failed checks can mean invalid Backend requests, connectivity or permission errors, or timeouts; incomplete results do not prove a conversation is absent.
- Report a target conversation's origin restriction using the exact tool reason. It is not a missing login or system approval request. Do not suggest granting unrelated permissions or retry the send through another path.
- Use wework_space for project-space operations and existing GitHub tools for CI checks. Delegated project runs cannot acquire personal control. Do not use personal API keys, direct storage reads or UI clicks to bypass a control permission error.
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.
- 2d ago First seen · 16 lines · 23 tokens per session scan A 8d7c35369c31
conversations is a skill published in the GitHub repository wecode-ai/Wegent (886 stars, last pushed today), licensed Apache-2.0. It adds 23 tokens to every session and 445 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-11-07.
conversations compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| conversationswecode-ai/Wegent | Skill | 886 | today | Apache-2.0 | A | 23 | Claude Code |
| lakefs-versioningoyi77/1ai-skills | Skill | 18 | today | MIT | A | 38 | Claude Code |
| git-github-workflowKroMiose/nekro-agent | Skill | 1.2k | 1mo ago | none | A | 101 | Claude Code |
| savevictusfate/scaffold | Skill | 7 | today | MIT | A | 90 | Claude Code, Codex |
| commit-message-generatorarmanzeroeight/fastagent-plugins | Skill | 29 | 3mo ago | MIT | A | 31 | Claude Code |
| caveman-helpHarmeet10000/skills | Skill | 7 | 6mo ago | MIT | A | 56 | Claude Code, Codex |
| gitasgeirtj/system_prompts_leaks | Skill | 71k | yesterday | CC0-1.0 | A | 163 | Claude Code |