Borrowing it
Nothing to install: this file belongs to DimitriGeelen/agentic-engineering-framework. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/DimitriGeelen/agentic-engineering-framework/master/.claude/commands/conversations.mdgit clone --depth 1 https://github.com/DimitriGeelen/agentic-engineering-frameworkWrote 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/commands/dimitrigeelen/agentic-engineering-framework/conversations)<a href="https://agentmods.dev/commands/dimitrigeelen/agentic-engineering-framework/conversations"><img src="https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/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/commands/dimitrigeelen/agentic-engineering-framework/conversations"><img src="https://agentmods.dev/badge/commands/dimitrigeelen/agentic-engineering-framework/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 | $0.00000 | $0.01267 |
| Opus 5.5 | $0.00000 | $0.00507 |
| Sonnet 5.5 | $0.00000 | $0.00253 |
| Haiku 4.5 | $0.00000 | $0.00127 |
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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/conversations — list active doorbell+mail threads on a topic (T-1864 wrapper)
Wraps scripts/agent-conversation-list.sh (T-1827). The "what cids are alive
on this topic?" verb — the orchestrator-view companion to the per-thread
status check.
Where /recent-chat and /recent-dm show CONTENT, this skill shows the
THREAD INDEX: which metadata.conversation_id values exist on a topic,
how many turns each has, who's posted, when the last activity was. Use it
when supervising N concurrent doorbell+mail threads and you need to see
your active set (and any abandoned/stalled ones to clean up).
Read-only by contract. Composes channel subscribe --json + jq under the
hood; the script handles PL-188 / PL-189 / PL-191 invariants.
Invocation:
| Form | Action |
|---|---|
/conversations <topic> |
List all cids on <topic> (default: 500 envelopes scanned, sorted by last_activity desc) |
/conversations <topic> --limit 1000 |
Larger scan (max 1000 per the underlying script) |
/conversations <topic> --sort turn_count |
Sort by turn count desc instead of last_activity |
/conversations <topic> --include-no-cid |
Add a sentinel (no-cid) row aggregating non-doorbell+mail envelopes |
/conversations <topic> --hub <addr> |
Single-hub mode (default: local) |
/conversations <topic> --json |
Machine-readable envelope for piping |
Step 1: Pre-flight
Run:
bash scripts/agent-conversation-list.sh --help >/dev/null 2>&1
If exit non-zero: stop. Print:
conversations: wrapper not found at scripts/agent-conversation-list.sh.
Ensure you're in the TermLink project root (cd /opt/termlink).
Step 2: Parse arguments
$ARGUMENTS is the operator's tail. Normalize:
-
The FIRST positional token (before any
--flag) is the required<topic>. -
If no positional is present, print a usage hint and exit:
conversations: <topic> required. Example: /conversations agent-chat-arc -
All other
--flagtokens pass through verbatim to the underlying script.
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.
- 1mo ago First seen · 137 lines · 0 tokens per session scan A a38ba5bedd9e
conversations is a command published in the GitHub repository DimitriGeelen/agentic-engineering-framework (18 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,267 tokens. 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 2026-09-04.
Other commands, from other repositories
cs-bizops
Top-level Business Operations router. Routes the inquiry to one of six BizOps sub-skills (process, vendor, capacity, comms, knowledge, procurement) and returns a digest. Invokes the business-operations-skills orchestrator (context: fork).
list
List recent task executions across all agents.
pause
Pause one or more schedules to temporarily stop automated executions.
gtd
Canonical GTD entry point for capture, clarification, organization, review, and engagement.
strict_full_cycle
Interactive workflow for the entire development cycle with every review gate forced on, ignoring the reviews a repository disabled in its configuration.
todo.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.