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/AbsoluteMode/session-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/absolutemode/session-recall/recall)<a href="https://agentmods.dev/commands/absolutemode/session-recall/recall"><img src="https://agentmods.dev/badge/commands/absolutemode/session-recall/recall/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/absolutemode/session-recall/recall"><img src="https://agentmods.dev/badge/commands/absolutemode/session-recall/recall.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 | $0.00021 | $0.00182 |
| Opus 5.5 | $0.00008 | $0.00073 |
| Sonnet 5.5 | $0.00004 | $0.00036 |
| Haiku 4.5 | $0.00002 | $0.00018 |
Grade A, and why
recall scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Recall the topic: "$ARGUMENTS" from the unified Claude Code + Codex + Cursor session index.
If the host exposes the dedicated recall subagent, dispatch it (in Claude Code:
subagent_type: session-recall:recall). Otherwise search iteratively with recent_sessions,
recall_search, expand_around/step, and grep.
Use a requested claude, codex, or cursor source filter; otherwise search all three. Return only a tight brief:
task, key decisions and why, tried/rejected approaches, current state, and
source + session_id + uuid pointers.
If "$ARGUMENTS" is empty, ask the user what to recall.
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 · 16 lines · 21 tokens per session scan A faccebc571d9
recall is a command published in the GitHub repository AbsoluteMode/session-recall (13 stars, last pushed 5d ago), licensed MIT. It adds 21 tokens to every session and 182 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 2026-08-30.
Other commands, from other repositories
screenshot
Screenshot a URL or document and read it visually.
bm
Ask basemind anything about the current codebase — outlines, refs, callers, git history, blame, diffs, docs, memory.
weekly
Weekly memory report — facts learned, procedures, repeated mistakes prevented.
recall
Recall what MemoRizz remembers about a topic, or about this project.
import-memory
Import a portable MemoRizz memory archive.
broadcast
Run broadcast on a distilled Raw — update related existing pages conversationally.