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 commands/cukas/remembrall/setup-remembrallgit clone --depth 1 https://github.com/cukas/remembrallWrote 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/cukas/remembrall/setup-remembrall)<a href="https://agentmods.dev/commands/cukas/remembrall/setup-remembrall"><img src="https://agentmods.dev/badge/commands/cukas/remembrall/setup-remembrall.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 | $0.00032 | $0.01822 |
| Opus 5 | $0.00016 | $0.00911 |
| Sonnet 5 | $0.00006 | $0.00364 |
| Haiku 4.5 | $0.00003 | $0.00182 |
Grade B, and why
setup-remembrall scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -q "claude-context-pct" ~/.claude/settings.json 2>/dev/null && echo "Bridge already installed" || echo "Bridge not found" How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup Remembrall Bridge (Manual Fallback)
Note: Since v2.3.0, the bridge auto-configures on first session start. You only need this command if auto-setup failed or you want to customize the Remembrall gauge.
Remembrall needs a small bridge in your Claude Code status line to feed context window % to its hooks. This command helps you add it.
You MUST complete ALL steps below (1–10). Do not stop after the bridge — the gauge and optional features are part of the setup flow.
What the Bridge Does
Your status line already has access to $remaining (context window % remaining) and $session_id. The bridge writes $remaining to a file in /tmp/claude-context-pct/ named by session_id. Each Claude session gets its own bridge file.
Steps
-
Check if the bridge already exists — Run:
grep -q "claude-context-pct" ~/.claude/settings.json 2>/dev/null && echo "Bridge already installed" || echo "Bridge not found" -
If already installed: Tell the user "Remembrall bridge is already set up." and continue to step 7.
-
If not installed: Read the user's current
~/.claude/settings.jsonand find thestatusLinesection. -
Find the insertion point — Look for the block that checks
if [ -n "$remaining" ]. The bridge snippet goes inside this block, before the closingfi. -
Show the user the bridge snippet they need to add inside their existing
if [ -n "$remaining" ]; then ... fiblock. The snippet requires$session_idto be extracted earlier in the status line (addsession_id=$(echo "$input" | jq -r '.session_id // empty');alongside the other extractions):
CTX_DIR="/tmp/claude-context-pct"; mkdir -p "$CTX_DIR" 2>/dev/null;
printf "%s" "$remaining" > "$CTX_DIR/${session_id}" 2>/dev/null;
- Edit the settings file — Insert the bridge snippet into the status line command. The exact location depends on the user's existing status line format. Find the
if [ -n "$remaining" ]block and add the bridge snippet inside it (after the existing context display logic, before thefi).
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 · 113 lines · 32 tokens per session scan B a505f7cd348e
setup-remembrall is a command published in the GitHub repository cukas/remembrall (6 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 1,822 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
handoff-resume
Resume from a prior session's handoff in .handoffs/.
handoff
Write a session handoff to .handoffs/ before context runs out.
datadog
Set up and troubleshoot Datadog — Agent deployment on Kubernetes, APM instrumentation, Log Management, Monitors, Dashboards, SLOs, Synthetic tests, and live incident investigation using the Datadog MCP server. Covers Terraform-managed Datadog resources.
linkerd
Linkerd-specific diagnostics — mTLS verification, proxy injection issues, authorization policy debugging, traffic management, and multi-cluster connectivity problems.
announce
Draft X/Twitter announcement post (or thread) for the latest plugin release.
build
Guided feature development with approval gates at each phase.