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.
git clone --depth 1 https://github.com/JansenAnalytics/claudexWrote 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/jansenanalytics/claudex/recap)<a href="https://agentmods.dev/commands/jansenanalytics/claudex/recap"><img src="https://agentmods.dev/badge/commands/jansenanalytics/claudex/recap/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/jansenanalytics/claudex/recap"><img src="https://agentmods.dev/badge/commands/jansenanalytics/claudex/recap.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 | $0.00015 | $0.00687 |
| Opus 5.5 | $0.00006 | $0.00275 |
| Sonnet 5.5 | $0.00003 | $0.00137 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
recap 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.
What it actually says
Build a terse "Done / In-flight / Next" recap of recent Claudex activity. Window from $ARGUMENTS (default today; 24h = last day; Nd = last N days). Pull from every source below — each is OPTIONAL, so never abort because one is missing; skip silently and move on.
-
Daily notes —
today/24h: read$HOME/.claude-agent/memory/YYYY-MM-DD.mdfor today's date. ForNd: glob the last N daily notes. Usels -t $HOME/.claude-agent/memory/*.md 2>/dev/null | head -Nthen Read each that exists. Extract decisions, completed tasks, problems/solutions. -
Event log — try, in order, robust to absence:
EL="${EVENT_LOG_HOME:-$HOME/projects/event-log}/event-log.cjs"; [ -f "$EL" ] && node "$EL" list --since <window> 2>/dev/null(fall back to--limit 30if--sinceunsupported)- else
[ -f ~/.openclaw/events.jsonl ] && tail -n 200 ~/.openclaw/events.jsonl | <filter to window>Summarize event types/highlights; don't dump raw JSON.
-
Own session activity — find Claudex's most-recently-touched Claude Code transcript:
SLUG=$(echo "$HOME/.claude-agent" | sed 's#[/.]#-#g'); F=$(ls -t "$HOME/.claude/projects/$SLUG"/*.jsonl 2>/dev/null | head -1)(Claude Code derives the project dir by replacing/and.with-). If it exists, pull assistant-text highlights, e.g.grep '"type":"assistant"' "$F" | tail -40 | jq -r 'try (.message.content[]? | select(.type=="text") | .text) catch empty' 2>/dev/null | grep -v '^$' | tail -15(fall back to plaingrep -o '"text":"[^"]*"'if jq fails). Distill 3-6 concrete things worked on — not raw lines. -
Git activity (optional) — quick scan of recent commits across projects:
for d in ~/projects/*/; do git -C "$d" log --since=<window> --oneline 2>/dev/null | sed "s|^|$(basename "$d"): |"; done | head -20. Note active repos/branches. Skip dirs that aren't repos.
Output: ONE Telegram-friendly message. Three bold headers — Done, In-flight, Next — bullets only, no markdown tables. Lead with a one-line window summary (e.g. Recap · today · 4 sources). Max ~22 lines. Infer "Next" from open todos / unfinished threads in the notes. If a source was empty, don't mention it. No padding, no congratulating.
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 · 25 lines · 15 tokens per session scan A 90cdb0c6ab58
recap is a command published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 687 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 2026-08-31.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
add-note
Add an internal or external note to a ConnectWise PSA ticket.
sync-linear
Sync current work with Linear ticket status.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.