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/joseairosa/recallWrote 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/joseairosa/recall/recall-update)<a href="https://agentmods.dev/commands/joseairosa/recall/recall-update"><img src="https://agentmods.dev/badge/commands/joseairosa/recall/recall-update.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 | $0.00000 | $0.00979 |
| Opus 5 | $0.00000 | $0.00490 |
| Sonnet 5 | $0.00000 | $0.00196 |
| Haiku 4.5 | $0.00000 | $0.00098 |
Grade C, and why
recall-update scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL "${RECALL_SERVER_URL}/install-hooks" | bash -s -- --api-key "${RECALL_API_KEY}" --server-url "${RECALL_SERVER_URL}" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Check whether this is a plugin install or a curl|bash install: How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Manually trigger a Recall plugin update, or toggle auto-update on/off.
Instructions
1. Detect install type
Check whether this is a plugin install or a curl|bash install:
[[ "${HOME}/.claude/plugins/recall/scripts/session-start.sh" -ef "$(which recall 2>/dev/null || true)" ]] \
&& echo "plugin" || true
ls "${HOME}/.claude/plugins/recall/scripts/session-start.sh" 2>/dev/null && echo "plugin" || echo "curl"
If the file exists at ~/.claude/plugins/recall/scripts/, it is a plugin install.
Otherwise it is a curl|bash install with scripts at ~/.claude/recall/hooks/.
2. Trigger the update
Plugin install:
Tell the user to run /plugin install recall in Claude Code — this re-installs the plugin at the latest version.
curl|bash install:
Read RECALL_SERVER_URL from ~/.claude/recall/config.json (default: https://recallmcp.com), then run:
RECALL_SERVER_URL="$(python3 -c "import json; d=json.load(open('${HOME}/.claude/recall/config.json')); print(d.get('server_url','https://recallmcp.com'))" 2>/dev/null || echo "https://recallmcp.com")"
RECALL_API_KEY="$(python3 -c "import json; d=json.load(open('${HOME}/.claude/recall/config.json')); print(d.get('api_key',''))" 2>/dev/null || echo "")"
curl -fsSL "${RECALL_SERVER_URL}/install-hooks" | bash -s -- --api-key "${RECALL_API_KEY}" --server-url "${RECALL_SERVER_URL}"
After the update completes, tell the user to restart Claude Code for the new hooks to take effect.
3. Show current version info (optional)
# Plugin: read from plugin.json
python3 -c "import json; d=json.load(open('${HOME}/.claude/plugins/recall/.claude-plugin/plugin.json')); print('Installed:', d.get('version','?'))" 2>/dev/null || true
# curl|bash: read from config.json
python3 -c "import json; d=json.load(open('${HOME}/.claude/recall/config.json')); print('Installed:', d.get('version','?'))" 2>/dev/null || true
# Available: check state.json
python3 -c "import json; d=json.load(open('${HOME}/.claude/recall/state.json')); print('Available:', d.get('available_version', 'up to date'))" 2>/dev/null || true
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.
- 8d ago First seen · 97 lines · 0 tokens per session scan C 66a5d3a5db46
recall-update is a command published in the GitHub repository joseairosa/recall (176 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 979 tokens. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
cost-report
Generate a local Claude Code cost report from the ECC cost-tracker metrics log.
cwb-relax
A command that searches for relaxing music in three styles: downtempo, acoustic folk, and nature ambience.
code-review
Code review a pull request.
analyze
Analyze Claude Code transcripts to surface subagent behavior and improvement opportunities.
t00-perf-check
A command that checks a Claude Code setup, including automatically loaded instructions, token use, skills, and hooks. It is described in Chinese and produces a configuration report with optimization suggestions.
t00-status
A status-report command for a T00 task workspace, using files that record communication, tasks, and the previous session's next steps.