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/raiyanyahya/recall/savegit clone --depth 1 https://github.com/raiyanyahya/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/raiyanyahya/recall/save)<a href="https://agentmods.dev/commands/raiyanyahya/recall/save"><img src="https://agentmods.dev/badge/commands/raiyanyahya/recall/save.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 | $0.00017 | $0.00252 |
| Opus 5 | $0.00009 | $0.00126 |
| Sonnet 5 | $0.00003 | $0.00050 |
| Haiku 4.5 | $0.00002 | $0.00025 |
Grade A, and why
save scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Generate (or overwrite) this project's context.md summary now, using Recall's
local offline summarizer.
Run with the Bash tool:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/make_context.py" || python "${CLAUDE_PLUGIN_ROOT}/scripts/make_context.py"
(make_context.py defaults to the current directory, so no --cwd is needed —
and on Windows passing the shell's $(pwd) would hand it a /c/... path that
doesn't match the transcript dir. The || python fallback covers Windows, where
the interpreter is normally python, not python3.)
Then report back:
- On success it prints the path it wrote and which summarizer path ran
(numpy-accelerated TextRank if numpy is present, otherwise the pure-Python
TextRank — both vendored, no install needed). Confirm the save and read back the
Goal and Where we left off lines from
.recall/context.md. - If it errored, surface the exact message.
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.
- 5d ago First seen · 27 lines · 17 tokens per session scan A bd871cf72831
save is a command published in the GitHub repository raiyanyahya/recall (745 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 252 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
resume
Resume a previous session. Reads recent session logs, open tasks, and last decisions — gives Claude full context without re-explaining the project.
ccr
CCR (Compressed Context with Retrieval) — recall the full original of context that greatcto compressed/filtered out, by its short id. The retrieval half of the compression layer.
reclaim-knowledge
Organize scattered professional material into a domain-based second-brain architecture. Maps existing sources (Canva, Drive, local folders, Notion, screenshots) to functional domains. Non-technical-friendly — produces folder structure + drag-and-drop instructions, not CLI commands.
save
Save this conversation as a new or existing reusable context.
orchestrate-brain
Weekly 30-minute second-brain review ritual. Orchestrates inbox clear, lightweight distillation, vault maintenance, cross-reference pass, and next-week capture focus. The compounding rhythm that keeps the system alive.