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-set-key)<a href="https://agentmods.dev/commands/joseairosa/recall/recall-set-key"><img src="https://agentmods.dev/badge/commands/joseairosa/recall/recall-set-key/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/joseairosa/recall/recall-set-key"><img src="https://agentmods.dev/badge/commands/joseairosa/recall/recall-set-key.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 | $0.01168 |
| Opus 5 | $0.00000 | $0.00584 |
| Sonnet 5 | $0.00000 | $0.00234 |
| Haiku 4.5 | $0.00000 | $0.00117 |
Grade C, and why
recall-set-key scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**b) ~/.claude/settings.json env section** — used by the plugin .mcp.json `${RECALL_API_KEY}` reference: Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
**b) ~/.claude/settings.json env section** — used by the plugin .mcp.json `${RECALL_API_KEY}` reference: How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update your Recall API key across every location Claude Code reads it from. Run this whenever you generate a new key from https://recallmcp.com/dashboard/keys.
Instructions
1. Ask for the new key
Use AskUserQuestion to prompt for the new API key. It starts with sk-. Never echo the full key back to the user in plain text.
2. Validate the key format
If the key does not start with sk-, stop and tell the user it looks invalid and to double-check they copied the full key from the dashboard.
3. Update all locations
Run each block below in order. Every location must be updated — missing any one of them will cause silent auth failures on next restart.
a) ~/.claude/recall/config.json — read by lifecycle hooks (session-start, observe, session-end) via lib/config.sh:
python3 - <<'PYEOF'
import json, os, stat
path = os.path.expanduser("~/.claude/recall/config.json")
os.makedirs(os.path.dirname(path), exist_ok=True)
try:
with open(path) as f:
config = json.load(f)
except Exception:
config = {}
config["api_key"] = "THE_API_KEY"
config.setdefault("server_url", "https://recallmcp.com")
with open(path, "w") as f:
json.dump(config, f, indent=2)
os.chmod(path, stat.S_IRUSR | stat.S_IWUSR)
print("✓ ~/.claude/recall/config.json")
PYEOF
b) ~/.claude/settings.json env section — used by the plugin .mcp.json ${RECALL_API_KEY} reference:
python3 - <<'PYEOF'
import json, os
path = os.path.expanduser("~/.claude/settings.json")
try:
with open(path) as f:
settings = json.load(f)
except Exception:
settings = {}
settings.setdefault("env", {})["RECALL_API_KEY"] = "THE_API_KEY"
with open(path, "w") as f:
json.dump(settings, f, indent=2)
print("✓ ~/.claude/settings.json")
PYEOF
c) ~/.claude.json mcpServers entry — the authoritative runtime config; takes precedence over env vars once registered:
python3 - <<'PYEOF'
import json, os
path = os.path.expanduser("~/.claude.json")
try:
with open(path) as f:
config = json.load(f)
except Exception:
config = {}
mcp = config.setdefault("mcpServers", {})
if "recall-remote" not in mcp:
mcp["recall-remote"] = {
"type": "http",
"url": "https://recallmcp.com/mcp",
"headers": {}
}
mcp["recall-remote"].setdefault("headers", {})["Authorization"] = "Bearer THE_API_KEY"
with open(path, "w") as f:
json.dump(config, f, indent=2)
print("✓ ~/.claude.json")
PYEOF
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.
- 9d ago First seen · 154 lines · 0 tokens per session scan C e5cf472a866a
recall-set-key is a command published in the GitHub repository joseairosa/recall (176 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,168 tokens. A static security scan graded it C with 2 findings (reads agent configuration directories, reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
export-closedloop-learnings
Exports pending ClosedLoop learnings to global location with deduplication.
pull-learnings
Pulls shared organization patterns into local org-patterns.toon.
revise-claude-md
Update CLAUDE.md with learnings from this session.
memory-distill
A periodic ritual: read the rolling tick log, propose promotions to permanent memory, and let the user confirm what to keep, archive, or forget.
capture
Model-driven lesson capture — read recent work in a role, distill genuine insights, append tagged bullets to pending.md. The real capture path; complements the Stop-hook's cheap regex fast-lane.
role-promote
Autonomously reconcile a role's memory — merge pending + recent learnings into ROLE.md, dedupe and declutter. The auto-promotion step fired when a role is stale (>7 days) with pending activity.