recall

recall is a command for coding agents from youdie006/sessionwiki. It costs 32 tokens per session (391 once invoked), scanned A, original, MIT.

A command that searches and summarizes earlier AI coding sessions using the local sessionwiki index.

In plain words
What is it for?
Use it to search past sessions, read the most relevant briefings, and identify the session to inspect or resume.
Why use it?
It reduces the effort of finding what was done before on a specific topic or project.

Command

Part of the sessionwiki plugin — 1 skill, 1 command, 1 hook shipped together

Install

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.

agentmods
npx agentmods add commands/youdie006/sessionwiki/recall
Clone the repo
git clone --depth 1 https://github.com/youdie006/sessionwiki

Or install sessionwiki, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 hook.

Wrote 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.

agentmods badge for recall

README.md
[![agentmods](https://agentmods.dev/badge/commands/youdie006/sessionwiki/recall.svg)](https://agentmods.dev/commands/youdie006/sessionwiki/recall)
Your own site
<a href="https://agentmods.dev/commands/youdie006/sessionwiki/recall"><img src="https://agentmods.dev/badge/commands/youdie006/sessionwiki/recall.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 391 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00032 $0.00391
Opus 5 $0.00016 $0.00196
Sonnet 5 $0.00006 $0.00078
Haiku 4.5 $0.00003 $0.00039

Measured 4d ago against content hash 306dadba749d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

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.

plugin/commands/recall.md · 42 lines

What it actually says

/recall - what did I do about "$ARGUMENTS"?

Search the user's past AI coding sessions for $ARGUMENTS and report what was done, using the local sessionwiki index. Read-only, offline.

Steps:

  1. Confirm the tool is present:

    command -v sessionwiki
    

    If empty, reply: "sessionwiki isn't installed (https://github.com/youdie006/sessionwiki) - nothing to recall." and stop.

  2. Search:

    sessionwiki search --json "$ARGUMENTS"
    
  3. From the JSON hits, take the 3-5 most relevant ids. For each, pull a briefing:

    sessionwiki brief --json <id>
    
  4. Summarize for the user, grouped by session, newest first. For each: the session id (short prefix), the project, the date, and 1-2 lines on what was asked and what the outcome was. End with the single most relevant session id so they can sessionwiki show <id> or resume it.

If search --json returns no hits, say so plainly ("No past session mentions '$ARGUMENTS'.") and suggest a broader or more specific topic. If a --json flag is rejected, rerun the same command without --json, read the plain text, and note the installed sessionwiki is older than the JSON output feature.

Changes

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.

  1. 4d ago First seen · 42 lines · 32 tokens per session scan A 306dadba749d

Subscribe to this mod's changes

recall is a command published in the GitHub repository youdie006/sessionwiki (5 stars, last pushed 14d ago), licensed MIT. It adds 32 tokens to every session and 391 once invoked, about $0.0002 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 2026-08-31.